Text-to-Speech

Also known as TTS

Ask about this topic

Overview

Text-to-speech systems turn text into speech that people can understand and use, with control over voice, accent, emotion, and speaking style. Common approaches include autoregressive models over speech-codec tokens, diffusion and flow-matching models, neural vocoders, and fine-tuning or preference-based post-training. Evaluation combines listening tests with measures such as word error rate and speaker similarity, using benchmarks for zero-shot cloning, multilingual synthesis, and instruction following. A central challenge is balancing intelligibility, speaker identity, and expressive appropriateness: high naturalness scores can miss pronunciation errors or poor fit to a domain, while low-resource languages and fast, robust generation remain difficult.

Latest papers

CardsList

67 papers4 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Jun 22, 2026

AudioCALM: Continuous Autoregressive Language Modeling for Universal Audio Generation

Unifying speech, sound, and music generation in one model is hindered by tradeoffs between fidelity, end-to-end training, in-context conditioning, and variable-length synthesis that no current paradigm fully resolves. To address this challenge, we present AudioCALM, a universal audio generation framework that extends autoregressive (AR) next-token prediction from discrete tokens to continuous audio latents: a thin flow-matching head replaces the softmax to predict rectified-flow velocities at each position, and a block-causal AR-Flow attention pattern produces arbitrary-length output. Joint training of multiple audio generation tasks faces an asymmetric text--audio mismatch: speech transcripts align to specific time spans and demand tight, time-aligned attention, whereas sound and music captions describe only overall semantics and rely on diffuse, holistic attention; mixing the two disproportionately degrades sound and music generation. We address this asymmetry at two levels: a data reformulation strategy that unifies all three tasks under a single description-style conditioning interface, and a novel architecture Asymmetric Mixture-of-Modality-Experts (A-MoME), which adds a dedicated residual expert for speech while sound and music share the backbone, incurring no inference overhead on non-speech inputs. Experimental results demonstrate that AudioCALM matches modality-specific state-of-the-art and outperforms prior unified baselines on speech, sound, and music generation benchmarks.

Huadai Liu, Kaicheng Luo, Wen Wang +4

Hong Kong University of Science and Technology (HKUST) · Tongyi Fun Team, Alibaba Group

Text-to-Audio GenerationFlow-Based Generative ModelingAudio GenerationText-to-Speech
AskPDF
Jun 22, 2026

Bagpiper-TTS: Natural Language Guided Universal Speech Synthesis

Classical TTS systems typically rely on rigid input formats and predefined metadata slots, limiting their ability to fulfill flexible user requirements. This paper introduces Bagpiper-TTS, a universal speech synthesis system that deals with diverse natural language user requests. Given a natural language prompt, Bagpiper-TTS first reasons over the users' intent to derive a rich caption, i.e., a comprehensive textual blueprint encompassing both transcription and nuanced metadata. Subsequently, this caption guides the synthesis of the target speech. Our model inherently supports a broad spectrum of tasks besides classical TTS applications, including multi-talker, intent-to-speech, role-play synthesis, singing voice synthesis, and more. Experimental results demonstrate that Bagpiper-TTS achieves an 1.7% Word Error Rate (WER) on the Seed-TTS-Eval benchmark and match the performance of dedicated models in both LLM-as-a-judge and human subjective evaluations across multiple applications.

Jinchuan Tian, Haoran Wang, Siddhant Arora +6

Language Technologies Institute, Carnegie Mellon University · LY Corporation · NVIDIA Research

Controllable Speech GenerationText-to-Speech
AskPDF
Jun 20, 2026

ISCSLP 2026 CoT-TTS Challenge: Chain-of-Thought Reasoning for Context-Aware Text-to-Speech

Recent advances in text-to-speech (TTS) have greatly improved speech naturalness, speaker similarity, and controllability. However, most existing controllable TTS systems still rely on explicit user-provided style prompts, making it difficult to automatically determine how a sentence should be spoken in long and complex conversational scenarios. This proposal introduces the ISCSLP 2026 CoT-TTS Challenge, which aims to evaluate whether a system can infer the intended speaking manner from contextual information and generate speech consistent with both the reasoning output and the surrounding scene. The challenge contains two tracks: text-context-aware CoT-TTS and audio-context-aware CoT-TTS. We construct a large-scale bilingual training set from speech-rich media and provide carefully filtered evaluation data for leaderboard comparison. Each system is required to output both a chain-of-thought reasoning analysis and the generated speech waveform. The official evaluation combines objective metrics, multimodal LLM-based evaluation, and human subjective assessment. To facilitate reproducibility, we provide inference code together with a fine-tuning recipe for a 0.6B Qwen3-based model trained via a three-stage strategy. This challenge is expected to support research on context understanding, chain-of-thought reasoning, and expressive speech generation for applications such as film dubbing, audiobook production, virtual characters, and spoken dialogue agents. Further information about the associated challenge is available at:https://iscslp2026-cot-tts.github.io/challenge-website/

Wei Xue, Junlan Feng, Shilei Zhang +9

The Hong Kong University of Science and Technology · China Mobile · Jiutian Artificial Intelligence Technology (Beijing) Co., Ltd., China Mobile +3

TTS SynthesisTTS EvaluationCoT ReasoningControllable Speech GenerationText-to-Speech
AskPDF
Jun 18, 2026

Exploring Pre-training Benefits on Phoneme Addition through Fine-tuning in Speech Synthesis

Transfer learning is widely used for low-resource text-to-speech. When the target corpus contains phonemes unseen in pre-training, the model must expand its phoneme inventory during fine-tuning; we call the process "phoneme addition." However, it remains unclear whether the pre-trained ability to generate seen phonemes contributes to this process. This study investigates phoneme addition in two settings: (1) a simulation setup using LLM-generated phoneme-controlled corpora that enables investigation without considering confounding factors, and (2) a real-speech cross-lingual transfer setup (English to Japanese) to validate whether the findings hold in practice. Experiments in both settings showed that while fine-tuning achieved higher naturalness than training from scratch, it required as much or more data to achieve comparable PER for new phonemes. These results indicate that pre-training mainly contributes to naturalness improvement, but offers limited benefit for phoneme addition.

Masato Murata, Koichi Miyazaki, Tomoki Koriyama +1

CyberAgent, Japan · Nagoya University, Japan

TTS SynthesisLow-Resource TTS SynthesisTransfer LearningText-to-Speech
AskPDF
Jun 16, 2026

Reliable Neural-Codec Text-to-Speech by ASR Self-Verification and Distillation: Near-Zero Catastrophic Failures Across Models and Codecs

Open autoregressive neural-codec text-to-speech (TTS) models sound excellent on typical inputs yet suffer stochastic catastrophic failures: on a meaningful fraction of utterances they emit silence, terminate early, or collapse into repetitive or hallucinated content. We show this failure mode is cheap to remove. Under a single format-robust metric (a catastrophic-failure rate via an ASR round-trip), best-of-N ASR self-verification drives failures to near-zero: no observed failures remain by N=2 on a standard corpus (LibriSpeech) and by N=4 on a hard prompt set. This is not an artifact of one model: the reduction replicates across four open codec-TTS systems and three neural codecs (XCodec2, SNAC, Mimi), reaching the near-zero floor by N=2 on three of the four. We then make the fix free at inference time by distilling the self-verified behaviour into the model, which recovers much of the robustness in single-shot decoding, closing ~52-58% of the failure mass on hard inputs at no test-time cost. The distillation gain concentrates where it is needed (hard inputs); on already-reliable prose there is no headroom and no detectable change. A controlled comparison adds a clean negative: offline direct preference optimization (DPO/IPO) does not beat plain supervised distillation, and an online iterative variant is promising but not statistically separable at our evaluation size. We report honestly the one model that resists (a larger Llasa where scale did not obviously help) and a rare-word capability ceiling that no self-distillation method overcomes

Ali Asaria, Tony Salomone, Deep Gandhi

Transformer Lab

TTS SynthesisText-to-Speech
AskPDF
Jun 15, 2026

Joycent: Multi-Accent TTS via Disentangled Accent Modeling and Layer-Specific Conditioning

Accent text-to-speech (TTS) aims to synthesize speech with a target accent while preserving speaker identity, but faces two key challenges: disentangling accent from speaker characteristics and effectively conditioning speech generation on the two disentangled factors. In this paper, we propose Joycent, a diffusion-based accent TTS framework that addresses both challenges. Our key idea is to separate accent and speaker information in both representation learning and TTS conditioning. Joycent uses WhisAID, a Whisper-based accent encoder with gradient reversal to learn speaker-disentangled accent representations, and introduces layer-specific conditional layer normalization to inject accent and speaker information at different stages of the text encoder. We evaluate Joycent on the Mandarin Regional Accent Corpus (MRAC) with seen and unseen speakers, including a challenging cross-accent setting where the speaker and accent prompts come from different accents. Experimental results show that Joycent improves accent similarity over existing methods while maintaining strong speaker similarity, with consistent gains under the challenging cross-accent setting. Subjective evaluation further confirms improved naturalness, accent similarity, and speaker preservation. The audio samples are available at https://oshindow.github.io/joycent/.

Xintong Wang, Junchuan Zhao, Ye Wang

School of Computing, National University of Singapore, Singapore

Disentangled Representation LearningTTS SynthesisText-to-Speech
AskPDF
Jun 10, 2026

SARA: A Dual-Stream VAE for High-Fidelity Speech Generation via Integrating Semantic and Acoustic Representations

Zero-shot text-to-speech (TTS) relies on robust speech representations. However, current speech tokenizers face a fundamental trade-off: acoustic codecs preserve high-fidelity audio but lack linguistic constraints, causing content errors during generation, whereas semantic tokens from self-supervised learning (SSL) models ensure precise text alignment but discard some acoustic information. To bridge this gap, we propose SARA, a dual-stream VAE that directly fuses a frozen SSL semantic anchor with a dedicated residual acoustic encoder. This effectively mitigates the dilemma, creating an efficient and compact latent space without relying on complex regularizers. SARA achieves superior reconstruction quality over strong baselines. Furthermore, in downstream zero-shot TTS tasks, it yields highly natural and expressive synthesis quality, and maintains robust generation performance even under accelerated inference, offering a favorable trade-off between synthesis speed and computational cost.

Peijie Chen, Wenhao Guan, Weijie Wu +7

School of Informatics, Xiamen University, China · School of Electronic Science and Engineering, Xiamen University, China · DiDi Global Inc., Beijing, China

Variational AutoencodersAudio Representation LearningSpeech ProcessingZero-Shot TTSText-to-Speech
AskPDF
Jun 8, 2026

OpenBibleTTS: Large-Scale Speech Resources and TTS Models for Low-Resource Languages

Recent advances in neural text-to-speech (TTS) and multilingual speech generation have substantially improved synthetic speech quality, yet these gains remain unevenly distributed across the world's languages. Existing models are still dominated by a small set of high-resource languages, while many studies of low-resource TTS are simulated on artificially downsampled high-resource corpora that do not reflect the orthographic variation and limited phonetic coverage encountered in genuinely underrepresented settings. As such, we introduce OpenBibleTTS, which is a large-scale benchmark for low-resource speech synthesis spanning 37 underrepresented languages. Moreover, a systematic comparison of various TTS architectures and large-scale speech generation models is conducted across in-domain Biblical text and out-of-domain material. Results show that no single system dominates across languages and metrics: Gemini-TTS achieves the highest listener ratings on most evaluated languages, but monolingual EveryVoice models trained on OpenBibleTTS remain strongest for intelligibility and are preferred in several African languages, while open from-scratch systems degrade sharply on out-of-domain text, revealing a persistent gap between broad multilingual coverage and reliable synthesis quality in underserved linguistic communities. We complement automatic evaluation with subjective human judgments, and open-source all processed datasets, alignments, and trained models to support future low-resource TTS research.

David Guzmán, Luel Hagos Beyene, Jesujoba Oluwadara Alabi +3

McGill University · Mila - Quebec AI Institute · AIMS Research and Innovation Centre +3

TTS SynthesisTTS EvaluationMultilingual TTS SynthesisLow-Resource TTS SynthesisText-to-Speech
AskPDF
Jun 8, 2026

NüshuVoice: Reviving the Voice of Endangered Nüshu with Pitch-Aware Text-to-Speech

Nüshu is an endangered phonetic script historically used by women in Jiangyong County, southern Hunan, China. While existing computational studies of Nüshu mainly focus on textual digitization and visual recognition, the acoustic reconstruction of its authentic pronunciation remains largely unexplored. Building a Nüshu text-to-speech (TTS) system is particularly challenging because available recordings are extremely limited and mostly consist of isolated syllable-level pronunciations rather than natural sentence-level utterances. In this work, we introduce NüshuVoice, the first TTS benchmark for Nüshu. We construct a sentence-level Nüshu text-to-audio dataset that aligns standardized Unicode Nüshu text, phonetic transcriptions, standard Chinese translations, and archival recordings. To synthesize speech under this extreme low-resource setting, we propose Nüshu-PitchVITS, an F0-conditioned VITS framework that leverages Nüshu's five-level pitch notation as an explicit prosodic inductive bias. Experimental results show that Nüshu-PitchVITS outperforms strong TTS baselines in spectral fidelity, pitch reconstruction, and human-rated intelligibility. We publicly release the dataset and code at: https://anonymous.4open.science/r/Nvshu-TTS-2EB6.

Hongkun Yang, Xinhui Yi, Xiyan Zhao +13

1Ocean University of China · 2The Hong Kong Polytechnic University · 3Cornell University +5

TTS SynthesisLow-Resource TTS SynthesisLow-Resource Language ProcessingText-to-Speech
AskPDF
Jun 8, 2026

TLDR: Compressing Audio Tokens for Efficient Autoregressive Text-to-Speech

Codec-based autoregressive (AR) speech language models have achieved strong text-to-speech (TTS) quality by modeling speech as sequences of discrete audio tokens with large pretrained backbones. However, this token-level formulation creates a structural efficiency bottleneck: speech-token sequences are much longer than text sequences, requiring the AR backbone to perform causal computation at every token position and maintain a KV cache that grows with the sequence length. We introduce TLDR, a patch-based autoregressive framework that accelerates codec-based AR-TTS by shifting the causal modeling from token-level speech sequences to patch-level sequences. TLDR groups consecutive codec tokens into compact latent patches using a lightweight compressor, models the resulting shorter patch sequence with a frozen pretrained AR-TTS backbone adapted by LoRA, and reconstructs fine-grained speech tokens within each patch using a speaker-conditioned extractor. With a patch size of 4, TLDR achieves a 1.8x inference speedup over the baseline AR-TTS model and reduces global KV-cache memory by up to 75%. Experimental results indicate that patch-level global causal modeling can be a practical way to reduce the inference cost of pretrained codec-based AR-TTS systems without replacing the existing modules.

Yejin Lee, Junwon Moon, Hyoeun Kim +3

Sungkyunkwan University · University of Seoul

Efficient Transformer InferenceAudio Token CompressionAudio TokenizationSpeech Language ModelsText-to-Speech
AskPDF
Jun 5, 2026

dots.tts Technical Report

We present dots.tts, a 2B-parameter continuous autoregressive text-to-speech (TTS) foundation model that models speech in a continuous latent space. Compared with existing continuous autoregressive models, our key innovations are threefold. First, we train an AudioVAE with multiple objectives to build a semantically structured and prediction-friendly continuous speech space. Second, we use full-history conditioning in the flow-matching head to preserve long-range consistency and reduce drift during generation. Third, we apply reward-free self-corrective post-training to the flow-matching head to further improve robustness and acoustic quality. After being trained on a large-scale multilingual corpus, dots.tts achieves the best average performance on Seed-TTS-Eval, with WERs of 0.94%/1.30%/6.60% and SIM scores of 81.0/77.1/79.5 on the zh/en/zh-hard test sets, respectively. Across other benchmarks, dots.tts also consistently demonstrates open-source state-of-the-art performance, exhibiting strong generation stability, voice cloning ability, and emotional expressiveness. For efficient inference, we further apply CFG-aware MeanFlow distillation, enabling low-latency speech generation with first-packet latencies of 85/54 ms in output streaming and dual-streaming modes, respectively. To facilitate reproducible research and practical deployment, we release the training and inference code, together with the pretrained, post-trained, and MeanFlow-distilled checkpoints, under the Apache 2.0 license.

Shi Lian, Changtao Li, Bohan Li +6

TTS SynthesisSpeech Foundation ModelsMultilingual TTS SynthesisText-to-Speech
AskPDF
Jun 5, 2026

VoxCPM2 Technical Report

We present VoxCPM2, a https://info.arxiv.org/help/prep#abstractsfully open-source multilingual and controllable speech generation foundation model that extends the hierarchical diffusion-autoregressive modeling paradigm of VoxCPM. VoxCPM2 advances the framework in three key dimensions: (i) capability, by unifying 30 languages, 9 Chinese dialects, natural-language voice design, style-controllable voice cloning, and high-fidelity continuation cloning within a single backbone; (ii) quality, through an asymmetric AudioVAE that encodes at 16 kHz and reconstructs at 48 kHz, enabling implicit super-resolution with high encoding efficiency; and (iii) scale, by jointly scaling the model to 2B parameters and the training data to over 2 million hours of multilingual speech. To support these diverse capabilities within one model, we introduce a unified sequence organization that expresses all generation modes through different arrangements of the same input building blocks, allowing joint training under a single set of parameters and objective. VoxCPM2 achieves state-of-the-art or competitive performance on public zero-shot and instruction-following TTS benchmarks. On our internal 30-language evaluation set, it attains an average WER of 1.68%. These results demonstrate that hierarchical continuous-latent modeling, without relying on any external discrete speech tokenizer, offers a viable and powerful foundation for large-scale multilingual and controllable speech generation. The model weights, fine-tuning code, and inference tools are publicly released under the Apache 2.0 license to foster community research and development.

Yixuan Zhou, Guoyang Zeng, Xin Liu +15

VoxCPM Team

Speech Foundation ModelsMultilingual TTS SynthesisControllable Speech GenerationSpeech Language ModelsAudio GenerationText-to-Speech+2
AskPDF
Jun 5, 2026

Leveraging Soft Distributions of SSL-Derived Discrete Speech Tokens for Downstream Inference

Discrete speech tokens obtained from self-supervised learning (SSL) models provide efficient data compression while maintaining strong performance, and have been widely used as intermediate representations in various tasks. However, discretization inevitably causes information loss, leading to degraded performance compared with continuous SSL features. In this work, we propose to apply soft token assignment only during downstream inference. This approach preserves the efficiency of hard discretization during training while enhancing the expressiveness of the tokens at inference. The proposed method outperforms conventional hard assignment on both ASR and speech synthesis tasks, and exhibits particularly strong generalizability to out-of-domain data. For ASR of non-native speech, it even surpasses models using continuous SSL features. Moreover, analysis of the resulting representations shows they align more accurately with phonemes compared with conventional hard assignment.

Kentaro Onda, Satoru Fukayama, Daisuke Saito +1

The University of Tokyo, Japan · National Institute of Advanced Industrial Science and Technology (AIST), Japan

Automatic Speech RecognitionAudio TokenizationSelf-Supervised Speech Representation LearningText-to-SpeechDiscrete Speech Representation Learning
AskPDF
May 29, 2026

ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment

Recent advancements in text-guided audio generation have yielded promising results in diverse domains, including sound effects, speech, and music. However, jointly generating speech with environmental audio remains challenging due to the inherent disparities in their acoustic patterns and temporal dynamics. We propose ImmersiveTTS, an environment-aware text-to-speech (TTS) model that generates natural speech seamlessly integrated within environmental contexts by explicitly modeling cross-modal interactions. Our model builds on a multimodal diffusion transformer and fuses transcript-aligned speech latent with text-conditioned environmental context via joint attention. To enhance semantic consistency, we introduce a domain-specific representation alignment objective tailored to environment-aware TTS, leveraging complementary self-supervised representations from speech and audio encoders. Experimental results show that ImmersiveTTS achieves higher naturalness, intelligibility, and audio fidelity than existing approaches across objective metrics and human listening tests.

Jun-Hak Yun, Seung-Bin Kim, Seong-Whan Lee

Department of Artificial Intelligence, Korea University, Seoul, Korea

Cross-Modal Representation LearningTTS SynthesisText-to-SpeechMultimodal Diffusion Models
AskPDF
May 28, 2026

MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks. To address this limitation, we introduce a discrete latent variable model on mel spectrograms that jointly optimizes the encoder and the speech language model. Joint optimization not only brings improvements over codec-based and other mel-spectrogram-based baselines on zero-shot Text-to-Speech (TTS) and Speech-to-Text (STT) tasks, but also effectively alleviates common issues in autoregressive mel spectrogram modeling, such as prolonged silence generation and word omissions.

Sung-Lin Yeh, Wei Zhou, Gil Keren +6

University of Edinburgh · *Work done at Meta · 2Google DeepMind +1

Audio Representation LearningAutoregressive Language ModelingAutomatic Speech RecognitionSpeech Language ModelsText-to-SpeechDiscrete Speech Representation Learning
AskPDF
May 26, 2026

PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech

Text-to-speech (TTS) evaluation for low-resource non-Latin-script languages can fail when it relies on a single ASR round-trip word error rate (WER). A system may produce no audio, speak a neighbouring language, preserve target script text only in an ASR transcript, or sound unnatural to native listeners. We introduce INSV (Intelligibility, Naturalness, Script fidelity, and Verification), a reporting framework that separates these cases. This paper reports INSV-A, the automated screening subset: synthesis completion, ASR WER/CER, transcript Script Fidelity Rate, and audio language identification. Native MOS and phonetic annotation are specified but not claimed in this release. We instantiate INSV-A as PashtoTTS-Bench, a dated benchmark for Pashto TTS. The April-May 2026 run evaluates Edge GulNawaz, Edge Latifa, OmniVoice clone, OmniVoice auto, and an Urdu negative control on 200 FLEURS and 200 filtered Common Voice 24 prompts. Under the independent omniASR_CTC_300M_v2, OmniVoice auto has the lowest WER (24.1% FLEURS, 27.4% CV24), followed by Edge GulNawaz (32.8%, 39.5%), Edge Latifa (35.6%, 47.7%), and OmniVoice clone (45.4%, 34.8%). WER below the natural-speech baseline reflects clean synthetic audio and should not be read as better than native speech. Whisper Large V3 returns 0.0% Pashto labels on checked Pashto TTS audio, while MMS-LID-4017 and SpeechBrain VoxLingua107 separate Pashto outputs from the Urdu control. The release provides provider metadata, per-sentence scores, LID audits, failure logs, and scripts for adding systems.

Hanif Rahman

aIndependent Researcher

Speech Generation EvaluationTTS EvaluationSpeech Quality AssessmentLow-Resource TTS SynthesisLow-Resource Language ProcessingText-to-Speech
AskPDF
May 25, 2026

CosyEdit2: Speech-Editing-Oriented Reinforcement Learning Unlocks Better Zero-Shot TTS

Speech editing and zero-shot Text-to-Speech (TTS) share a similar generative foundation conditioned on speech prompts, yet speech editing demands far stricter local acoustic consistency with surrounding unedited content. While prior work has shown that Supervised Fine-Tuning (SFT) enables TTS models to acquire functional editing capability, this approach remains fundamentally bottlenecked by imperfect paired editing data and coarse-grained optimization signals. To address these limitations, we propose CosyEdit2, a speech editing model built on a two-stage post-training framework that progresses from supervised editing initialization to editing-oriented Group Relative Policy Optimization (GRPO) over target-speech-free data. Extensive experiments demonstrate that CosyEdit2 not only substantially advances speech editing performance, but also unlocks better zero-shot TTS capability, revealing a deeper mutual relationship between the two tasks. Audio samples are available at https://cjy1018.github.io/CosyEdit2.

Junyang Chen, Yuhang Jia, Hui Wang +3

College of Computer Science, Nankai University · College of Artificial Intelligence, Nankai University

Speech EditingZero-Shot TTSText-to-Speech
AskPDF
May 21, 2026

Eroding Trust in Real Speech: A Large-Scale Study of Human Audio Deepfake Perception

Audio deepfakes have improved rapidly recently, yet their effect on human trust in real speech remains unstudied. We present the largest listening study on audio deepfake perception to date, collecting 35,532 judgments from 1,768 participants across 138 text-to-speech and voice conversion systems. Our central finding is a skepticism shift: compared to a 2021 baseline, human accuracy on fake samples barely changed (72.9% to 71.2%), but accuracy on real samples dropped from 72.7% to 64.1%. Participants are not worse at detecting synthesis artifacts; rather, they increasingly distrust authentic speech. Samples generated by commercial and autoregressive language model systems proved hardest to detect (61.3 - 65.9%), while those from traditional seq2seq and flow-matching models remain easier to spot (75.4 - 76.8%). An ML detector that served as a reference point maintained over 94.5% accuracy across all conditions. Our results suggest that the primary threat posed by modern deepfakes may not be mere deception, but the erosion of trust in genuine audio.

Nicolas M. Müller, Wei Herng Choong

Fraunhofer AISEC & Resemble AI · Germany · Fraunhofer AISEC

Audio Deepfake DetectionSpeech ProcessingTrust in AIText-to-Speech
AskPDF
May 20, 2026

DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech

Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker identity. We discover that emotion embedding emerges as a linearly decodable direction of frozen hidden states, nearly orthogonal to the direction embedding speaker identity. This inspires a plug-and-play framework DUET for emotion control over pretrained diffusion and flow-matching based TTS models. During generation, DUET unifies dual-space control to achieve fine-grained emotion intervention in a single per-step update: hidden space steering shifts generation along the target emotion direction, while mel-space guidance refines spectral details through gradients backpropagated from a differentiable vocoder. We validate DUET on five architecturally diverse pretrained TTS backbones across three datasets, where it outperforms 10 supervised state-of-the-art emotional TTS baselines across paradigms and achieves the highest human-rated emotion appropriateness. To further showcase its qualitative behavior, we deploy DUET on an Ameca humanoid robot, where it produces richly expressive emotional speech on the humanoid, demonstrating the strong potential for plug-and-play affective interaction for embodied agents.

Xu Zhang, Longbing Cao, Zhangkai Wu

Frontier AI Research Centre, Macquarie University, Sydney, NSW, Australia

TTS SynthesisAudio Diffusion ModelsControllable Speech GenerationText-to-SpeechEmotional Speech Synthesis
AskPDF
May 7, 2026

WavCube: Unifying Speech Representation for Understanding and Generation via Semantic-Acoustic Joint Modeling

Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant compatibility challenges. Typically, semantics-oriented features are learned from self-supervised learning (SSL), and acoustic-oriented features from reconstruction. Such fragmented representations hinder the realization of truly unified speech systems. We present WavCube, a compact continuous latent derived from an SSL speech encoder that simultaneously supports speech understanding, reconstruction, and generation. WavCube employs a two-stage training scheme. Stage 1 trains a semantic bottleneck to filter off-manifold redundancy that makes raw SSL features intractable for diffusion. Stage 2 injects fine-grained acoustic details via end-to-end reconstruction, while a semantic anchoring loss ensures the representation remains grounded within its original semantic manifold. Comprehensive experiments show that WavCube closely approaches WavLM performance on SUPERB despite an 8x dimensional compression, attains reconstruction quality on par with existing acoustic representations, delivers state-of-the-art zero-shot TTS performance with markedly faster training convergence, and excels in speech enhancement, separation, and voice conversion tasks on the SUPERB-SG benchmark. Systematic ablations reveal that WavCube's two-stage recipe resolves two intrinsic flaws of SSL features for generative modeling, paving the way for future unified speech systems. Codes and checkpoints are available at https://github.com/yanghaha0908/WavCube.

Guanrou Yang, Tian Tan, Qian Chen +12

Shanghai Jiao Tong University · Independent Researcher · Shanghai Innovation Institute +4

Audio Representation LearningTTS SynthesisSpeech Foundation ModelsAudio UnderstandingSelf-Supervised Speech Representation LearningText-to-Speech
AskPDF
May 5, 2026

MiniMind-O Technical Report: An Open Small-Scale Speech-Native Omni Model

MiniMind-O is an open 0.1B-scale omni model built on the MiniMind language model. It accepts text, speech, and image inputs, and returns both text and streaming speech. The release includes model code, checkpoints, and the main Parquet training datasets for text-to-audio, image-to-text, and audio-to-audio training, making the complete interaction loop directly inspectable. The model uses a full MiniMind backbone as the Thinker and an independent four-layer Talker made from MiniMind blocks. Frozen SenseVoice-Small and SigLIP2 encoders provide speech and image features, which are mapped by lightweight MLP projectors and injected at modality-placeholder positions. The Talker reads a middle-layer Thinker state together with an autoregressive eight-layer Mimi-code buffer. Speaker control is handled by a dedicated speaker token, right-aligned reference codec prompts, and precomputed CAM++ speaker embeddings, so voice conditioning remains part of the audio-code context rather than a separate TTS module. With a 768-dimensional Talker, the dense and MoE variants reach average CERs of 0.0897 and 0.0900 in Thinker--Talker consistency evaluation, with overall voice-cloning similarities of 0.5995 and 0.5937. Beyond reporting a working system, the paper identifies three scale-critical design choices for small omni models: middle-layer semantic bridging, a released multimodal sequence format, and a parameter-efficient eight-codebook interface.

Jingyao Gong

Independent Researcher

Speech Foundation ModelsUnified Multimodal ModelsSmall Language ModelsAudio-Language ModelsMultimodal Foundation ModelsAudio Generation+2
AskPDF
Apr 30, 2026

JaiTTS: A Thai Voice Cloning Model

We present JaiTTS-v1.0, a state-of-the-art Thai voice cloning text-to-speech model built through continual training on a large Thai-centric speech corpus. The model architecture is adapted from VoxCPM, a tokenizer-free autoregressive TTS model. JaiTTS-v1.0 directly processes numerals and Thai-English code-switching, which is very common in realistic settings, without explicit text normalization. We test the models on short- and long-duration speech generation, which reflects many real-world use cases. JaiTTS-v1.0 achieves a state-of-the-art CER of 1.94%, surpassing the human ground truth of 1.98% for short-duration tasks while performing on par with human ground truth for long-duration tasks. In human judgment evaluations, our model wins 283 of 400 pairwise comparisons against commercial flagships, with only 58 losses. Our code and demo are available at https://github.com/JTS-AI-Team/JaiTTS .

Jullajak Karnjanaekarin, Pontakorn Trakuekul, Narongkorn Panitsrisit +5

Jasmine Technology Solution · Sirindhorn International Institute of Technology · Department of Linguistics, Chulalongkorn University

TTS SynthesisAudio GenerationText-to-SpeechVoice Cloning
AskPDF
Apr 28, 2026

One Voice, Many Tongues: Cross-Lingual Voice Cloning for Scientific Speech

Preserving a speaker's voice identity while generating speech in a different language remains a fundamental challenge in spoken language technology, particularly in specialized domains such as scientific communication. In this paper, we address this challenge through our system submission to the International Conference on Spoken Language Translation (IWSLT 2026), the Cross-Lingual Voice Cloning shared task. First, we evaluate several state-of-the-art voice cloning models for cross-lingual speech generation of scientific texts in Arabic, Chinese, and French. Then, we build voice cloning systems based on the OmniVoice foundation model. We employ data augmentation via multi-model ensemble distillation from the ACL 60/60 corpus. We investigate the effect of using this synthetic data for fine-tuning, demonstrating improvements in intelligibility (WER & CER) and speaker similarity (SIM), with gains varying across languages.

Amanuel Gizachew Abebe, Yasmin Moslem

Shaggar Institute of Technology · Shaggar City, Ethiopia · Trinity College Dublin +1

TTS SynthesisText-to-SpeechVoice Cloning
AskPDF
Apr 28, 2026

Praxy Voice: Voice-Prompt Recovery + BUPS for Commercial-Class Indic TTS from a Frozen Non-Indic Base at Zero Commercial-Training-Data Cost

Commercial TTS systems produce near-native Indic audio, but the best open-source bases (Chatterbox, Indic Parler-TTS, IndicF5) trail them on measured phonological dimensions, and the most widely adopted multilingual base (Chatterbox, 23 languages) does not even tokenise Telugu or Tamil. We ask: what is the minimum intervention that brings such a non-Indic-native base to commercial-class output on Telugu, Tamil, and Hindi, without training a new acoustic decoder and without any commercial TTS training data? We combine three pieces: (1) BUPS, a Brahmic Unified Phoneme Space that deterministically romanises seven Indic scripts to ISO-15919 so Chatterbox's Latin tokeniser can process them; (2) a LoRA adapter on only the text-token predictor (Chatterbox's t3), trained on ~1,220h of licensed Indic audio with a Hindi-proxy language_id; (3) a voice-prompt recovery recipe -- an 8-11s same-language reference clip plus three sampling overrides (exaggeration 0.7, temperature 0.6, min_p 0.1; "Config B") -- that recovers commercial-class acoustic output with no acoustic-decoder training. On Hindi, the LoRA regresses accuracy and we instead use vanilla Chatterbox + Config B, giving a two-branch deployment. Evaluated on 10-utterance pilot sets with the companion PSP benchmark, Praxy Voice matches or slightly leads commercial baselines: 26.7% retroflex collapse on Telugu (vs Sarvam Bulbul 33.3%), 71% Tamil-zha collapse (vs commercial trio's 86%), 0.025 LLM-WER on Hindi (tied with Cartesia Sonic-3). For intra-sentential code-mix we add a third branch (IndicF5 + native-script transliteration) that drops code-mix LLM-WER from 0.80-0.85 to 0.14-0.27 across Hi/Te/Ta. We release R6 LoRA weights (Apache-2.0), inference code and router (MIT), and a Gradio demo.

Venkata Pushpak Teja Menta

Praxel Ventures

TTS SynthesisMultilingual TTS SynthesisText-to-Speech
AskPDF
Apr 24, 2026

TTS-PRISM: A Perceptual Reasoning and Interpretable Speech Model for Fine-Grained Diagnosis

While generative text-to-speech (TTS) models approach human-level quality, monolithic metrics fail to diagnose fine-grained acoustic artifacts or explain perceptual collapse. To address this, we propose TTS-PRISM, a multi-dimensional diagnostic framework for Mandarin. First, we establish a 12-dimensional schema spanning stability to advanced expressiveness. Second, we design a targeted synthesis pipeline with adversarial perturbations and expert anchors to build a high-quality diagnostic dataset. Third, schema-driven instruction tuning embeds explicit scoring criteria and reasoning into an efficient end-to-end model. Experiments on a 1,600-sample Gold Test Set show TTS-PRISM outperforms generalist models in human alignment. Profiling six TTS paradigms establishes intuitive diagnostic flags that reveal fine-grained capability differences. TTS-PRISM is open-source, with code and checkpoints at https://github.com/xiaomi-research/tts-prism.

Xi Wang, Jie Wang, Xingchen Song +8

Tsinghua University, China · MiLM Plus, Xiaomi Inc., China · The University of Tokyo, Japan

TTS SynthesisSpeech Generation EvaluationTTS EvaluationSpeech Quality AssessmentText-to-Speech
AskPDF
Apr 20, 2026

MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech

Instruction-following text-to-speech (TTS) has emerged as an important capability for controllable and expressive speech generation, yet its evaluation remains underdeveloped due to limited benchmark coverage, weak diagnostic granularity, and insufficient multilingual support. We present MINT-Bench, a comprehensive multilingual benchmark for instruction-following TTS. MINT-Bench is built upon a hierarchical multi-axis taxonomy, a scalable multi-stage data construction pipeline, and a hierarchical hybrid evaluation protocol that jointly assesses content consistency, instruction following, and perceptual quality. Experiments across ten languages show that current systems remain far from solved: frontier commercial systems lead overall, while leading open-source models become highly competitive and can even outperform commercial counterparts in localized settings such as Chinese. The benchmark further reveals that harder compositional and paralinguistic controls remain major bottlenecks for current systems. We release MINT-Bench together with the data construction and evaluation toolkit to support future research on controllable, multilingual, and diagnostically grounded TTS evaluation. The leaderboard and demo are available at https://longwaytog0.github.io/MINT-Bench/

Huakang Chen, Jingbin Hu, Liumeng Xue +12

School of Intelligence Science and Technology, Nanjing University, Suzhou, China · Yutu Zhineng, Beijing, China · Lingguang Zhaxian Technology, Shanghai, China

TTS SynthesisSpeech Generation EvaluationTTS EvaluationMultilingual TTS SynthesisControllable Speech GenerationText-to-Speech
AskPDF
Apr 13, 2026

Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization Alignment

Speech Language Models (SLMs) exhibit strong semantic understanding, yet often fail to translate this capacity into expressive acoustic realization, producing speech with flattened prosody and misaligned emotion. We identify this mismatch as the semantic understanding-acoustic realization gap. Existing approaches typically rely on externally specified proxies, such as emotion labels or style prompts, which require annotations and struggle to capture dynamically evolving expressive intent throughout dialogue. To overcome these limitations, we propose SASLM (Self-Aware Speech Language Model), a proxy-free framework that bridges what the model thinks and how it speaks through self-aware intent-realization alignment: (1) Intent-Aware Bridging self-distills expressive intent from the model's own evolving semantic generation states via a Variational Information Bottleneck (VIB), thereby guiding expressive speech realization without external expressive supervision; while (2) Realization-Aware Alignment reflectively aligns generated acoustics with intended expression through self-reward optimization, progressively improving intent-realization consistency during speech generation. Despite using only 3B parameters and 800 hours of expressive speech data, SASLM achieves state-of-the-art performance on EchoMind among open-source systems, surpassing models over 10 times larger and approaching commercial systems.

Kuang Wang, Lai Wei, Ping Lin +8

The Chinese University of Hong Kong, Shenzhen · Tencent Ethereal Audio Lab · Southeast University +2

Expressive Speech SynthesisSpeech Language ModelsText-to-SpeechControllable Speech GenerationEmotional Speech Synthesis
AskPDF
Apr 12, 2026

Sign-to-Speech Prosody Transfer via Sign Reconstruction-based GAN

Deep learning models have improved sign language-to-text translation and made it easier for non-signers to understand signed messages. When the goal is spoken communication, a naive approach is to convert signed messages into text and then synthesize speech via Text-to-Speech (TTS). However, this two-stage pipeline inevitably treat text as a bottleneck representation, causing the loss of rich non-verbal information originally conveyed in the signing. To address this limitation, we propose a novel task, Sign-to-Speech Prosody Transfer, which aims to capture the global prosodic nuances expressed in sign language and directly integrate them into synthesized speech. A major challenge is that aligning sign and speech requires expert knowledge, making annotation extremely costly and preventing the construction of large parallel corpora. To overcome this, we introduce SignRecGAN, a scalable training framework that leverages unimodal datasets without cross-modal annotations through adversarial learning and reconstruction losses. Furthermore, we propose S2PFormer, a new model architecture that preserves the expressive power of existing TTS models while enabling the injection of sign-derived prosody into the synthesized speech. Extensive experiments demonstrate that the proposed method can synthesize speech that faithfully reflects the emotional content of sign language, thereby opening new possibilities for more natural sign language communication. Our code will be available upon acceptance.

Toranosuke Manabe, Yuto Shibata, Shinnosuke Takamichi +1

Keio University, Yagami Campus, Yokohama Kanagawa 223-8522, Japan

Generative Adversarial NetworksText-to-Speech
AskPDF
Mar 23, 2026

SelfTTS: cross-speaker style transfer through explicit embedding disentanglement and self-refinement using self-augmentation

This work presents SelfTTS, a text-to-speech (TTS) model designed for cross-speaker style transfer that eliminates the need for external pre-trained speaker or emotion encoders. The architecture achieves emotional expressivity in neutral speakers through an explicit disentanglement strategy utilizing Gradient Reversal Layers (GRL) combined with cosine similarity loss to decouple speaker and emotion information. We introduce Multi Positive Contrastive Learning (MPCL) to induce clustered representations of speaker and emotion embeddings based on their respective labels. Furthermore, SelfTTS employs a self-refinement strategy via Self-Augmentation, exploiting the model's voice conversion capabilities to enhance the naturalness of synthesized speech. Experimental results demonstrate that SelfTTS achieves superior emotional naturalness (eMOS) and robust stability in target timbre and emotion compared to state-of-the-art baselines.

Lucas H. Ueda, João G. T. Lima, Pedro R. Corrêa +3

Universidade Estadual de Campinas (UNICAMP), Brazil · CPQD, Brazil

Disentangled Representation LearningTTS SynthesisSpeech ProcessingControllable Speech GenerationText-to-SpeechEmotional Speech Synthesis
AskPDF
Mar 21, 2026

The Binding Effect: Analyzing How Multi-Dimensional Cues Form Gender Bias in Instruction TTS

Current bias evaluations in Instruction Text-to-Speech (ITTS) often rely on univariate testing, overlooking the compositional structure of social cues. In this work, we investigate gender bias by modeling prompts as combinations of Social Status, Career stereotypes, and Persona descriptors. Analyzing open-source ITTS models, we uncover systematic interaction effects where social dimensions modulate one another, creating complex bias patterns missed by univariate baselines. Crucially, our findings indicate that these biases extend beyond surface-level artifacts, demonstrating strong associations with the semantic priors of pre-trained text encoders and the skewed distributions inherent in training data. We further demonstrate that generic diversity prompting is insufficient to override these entrenched patterns, underscoring the need for compositional analysis to diagnose latent risks in generative speech.

Kuan-Yu Chen, Yi-Cheng Lin, Po-Chung Hsieh +5

Graduate Institute of Communication Engineering, National Taiwan University, Taiwan · AI Research Center, Inventec Corporation, Taiwan

Text-to-SpeechSocial Bias in Language ModelsTTS Evaluation
AskPDF