TTS Synthesis

TTS: Text-to-Speech

Follow this topic Ask about this topic

Text-to-speech synthesis studies how to turn written language into speech while preserving words, pronunciation, and the intended voice and delivery. Systems range from autoregressive models that generate speech tokens in sequence to parallel methods such as flow matching and diffusion, often using speaker prompts, phonetic alignment, or prosody controls. Current work extends these methods to multilingual and low-resource languages, expressive speech, long-form output, and low-latency streaming. A central challenge is balancing intelligibility, naturalness, speaker identity, and fine-grained control, while evaluations based on overall quality scores may miss errors in pronunciation, accent, or context.

Latest papers

275 papers49 papers in the last four weeks, up 17% on the four weeks before. 0.3% of all new papers.

Mar 18, 2026

MOSS-TTS Technical Report

This technical report presents MOSS-TTS, a speech generation foundation model built on a scalable recipe: discrete audio tokens, autoregressive modeling, and large-scale pretraining. Built on MOSS-Audio-Tokenizer, a causal Transformer tokenizer that compresses 24 kHz audio to 12.5 fps with variable-bitrate RVQ and unified semantic-acoustic representations, we release two complementary generators: MOSS-TTS, which emphasizes structural simplicity, scalability, and long-context/control-oriented deployment, and MOSS-TTS-Local-Transformer, which introduces a frame-local autoregressive module for higher modeling efficiency, stronger speaker preservation, and a shorter time to first audio. Across multilingual and open-domain settings, MOSS-TTS supports zero-shot voice cloning, token-level duration control, phoneme-/pinyin-level pronunciation control, smooth code-switching, and stable long-form generation. This report summarizes the design, training recipe, and empirical characteristics of the released models.

Yitian Gong, Botian Jiang, Yiwei Zhao +23

TTS Synthesis Speech Foundation Models Zero-Shot TTS Controllable Speech Generation Discrete Speech Representation Learning

Mar 17, 2026

CAST-TTS: A Simple Cross-Attention Framework for Unified Timbre Control in TTS

Current Text-to-Speech (TTS) systems typically use separate models for speech-prompted and text-prompted timbre control. While unifying both control signals into a single model is desirable, the challenge of cross-modal alignment often results in overly complex architectures and training objective. To address this challenge, we propose CAST-TTS, a simple yet effective framework for unified timbre control. Features are extracted from speech prompts and text prompts using pre-trained encoders. The multi-stage training strategy efficiently aligns the speech and projected text representations within a shared embedding space. A single cross-attention mechanism then allows the model to use either of these representations to control the timbre. Extensive experiments validate that the unified cross-attention mechanism is critical for achieving high-quality synthesis. CAST-TTS achieves performance comparable to specialized single-input models while operating within a unified architecture. The demo page can be accessed at https://HiRookie9.github.io/CAST-TTS-Page.

Zihao Zheng, Wen Wu, Chao Zhang +2

Shanghai AI Lab, China · MoE Key Lab of Artificial Intelligence, X-LANCE Lab, Shanghai Jiao Tong University, China

TTS Synthesis Controllable Speech Generation Voice Cloning

Mar 17, 2026

WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models

Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention. In this paper, we propose WAND, Windowed Attention and Knowledge Distillation, a framework that adapts pretrained AR-TTS models to operate with constant computational and memory complexity. WAND separates the attention mechanism into two: persistent global attention over conditioning tokens and local sliding-window attention over generated tokens. To stabilize fine-tuning, we employ a curriculum learning strategy that progressively tightens the attention window. We further utilize knowledge distillation from a full-attention teacher to recover high-fidelity synthesis quality with high data efficiency. Evaluated on three modern AR-TTS models, WAND preserves the original quality while achieving up to 66.2% KV cache memory reduction and length-invariant, near-constant per-step latency.

Hanna Lee, Tan Dat Nguyen, Jaehoon Kang +1

Korea Advanced Institute of Science and Technology, Republic of Korea · Sungkyunkwan University, Republic of Korea

TTS Synthesis Self-Attention KV-Cache Management Sparse Attention Sliding-Window Attention Attention Mechanisms

Mar 16, 2026

NV-Bench: Benchmark of Nonverbal Vocalization Synthesis for Expressive Text-to-Speech Generation

While recent text-to-speech (TTS) systems increasingly integrate nonverbal vocalizations (NVs), their evaluations lack standardized metrics and reliable ground-truth references. To bridge this gap, we propose NV-Bench, the first benchmark grounded in a functional taxonomy that treats NVs as communicative acts rather than acoustic artifacts. NV-Bench comprises 1,651 multi-lingual, in-the-wild utterances with paired human reference audio, balanced across 14 NV categories. We introduce a dual-dimensional evaluation protocol: (1) Instruction Alignment, utilizing the proposed paralinguistic character error rate (PCER) to assess controllability, (2) Acoustic Fidelity, measuring the distributional gap to real recordings to assess acoustic realism. We evaluate diverse TTS models and develop two baselines. Experimental results demonstrate a strong correlation between our objective metrics and human perception, establishing NV-Bench as a standardized evaluation framework.

Qinke Ni, Huan Liao, Dekun Chen +2

The Chinese University of Hong Kong, Shenzhen

Nonverbal Vocalization Generation Expressive Speech Synthesis TTS Synthesis Speech Generation Evaluation TTS Evaluation

Mar 16, 2026

WhispSynth: Scaling Multilingual Whisper Corpus through Real Data Curation and A Novel Pitch-free Generative Framework

Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus constructed via a novel high-fidelity generative framework. Specifically, we propose a pipeline integrating Differentiable Digital Signal Processing (DDSP)-based pitch-free method with Text-to-Speech (TTS) models. This framework refines a comprehensive collection of resources, including our newly constructed WhispNJU dataset, into 118 hours of high-fidelity whispered speech from 479 speakers. Unlike standard synthetic or noisy real data, our data engine faithfully preserves source vocal timbre and linguistic content while ensuring acoustic consistency, providing a robust foundation for text-to-whisper research. Experimental results demonstrate that WhispSynth exhibits significantly higher quality than existing corpora. Moreover, our CosyWhisper, tuned with WhispSynth, achieves speech naturalness on par with ground-truth samples. The official implementation and related resources are available at https://github.com/tan90xx/cosywhisper.

Tianyi Tan, Jiaxin Ye, Yuanming Zhang +4

Key Laboratory of Modern Acoustics, Nanjing University, Nanjing 210093, China · Fudan University, Shanghai, China · ByteDance, China

Speech Processing TTS Synthesis

Mar 15, 2026

DiFlowDubber: Discrete Flow Matching for Automated Video Dubbing via Cross-Modal Alignment and Synchronization

Video dubbing requires content accuracy, expressive prosody, high-quality acoustics, and precise lip synchronization, yet existing approaches struggle on all four fronts. To address these issues, we propose DiFlowDubber, the first video dubbing framework built upon a discrete flow matching backbone with a novel two-stage training strategy. In the first stage, a zero-shot text-to-speech (TTS) system is pre-trained on large-scale corpora, where a deterministic architecture captures linguistic structures, and the Discrete Flow-based Prosody-Acoustic (DFPA) module models expressive prosody and realistic acoustic characteristics. In the second stage, we propose the Content-Consistent Temporal Adaptation (CCTA) to transfer TTS knowledge to the dubbing domain: its Synchronizer enforces cross-modal alignment for lip-synchronized speech. Complementarily, the Face-to-Prosody Mapper (FaPro) conditions prosody on facial expressions, whose outputs are then fused with those of the Synchronizer to construct rich, fine-grained multimodal embeddings that capture prosody-content correlations, guiding the DFPA to generate expressive prosody and acoustic tokens for content-consistent speech. Experiments on two benchmark datasets demonstrate that DiFlowDubber outperforms prior methods across multiple evaluation metrics.

Ngoc-Son Nguyen, Thanh V. T. Tran, Jeongsoo Choi +3

FPT Software AI Center, Vietnam · KAIST, South Korea · Independent researcher, work done in part while author was at the FPT Software AI Center, Vietnam. +1

Expressive Speech Synthesis TTS Synthesis Audio-Visual Alignment

Mar 12, 2026

Causal Prosody Mediation for Text-to-Speech:Counterfactual Training of Duration, Pitch, and Energy in FastSpeech2

We propose a novel causal prosody mediation framework for expressive text-to-speech (TTS) synthesis. Our approach augments the FastSpeech2 architecture with explicit emotion conditioning and introduces counterfactual training objectives to disentangle emotional prosody from linguistic content. By formulating a structural causal model of how text (content), emotion, and speaker jointly influence prosody (duration, pitch, energy) and ultimately the speech waveform, we derive two complementary loss terms: an Indirect Path Constraint (IPC) to enforce that emotion affects speech only through prosody, and a Counterfactual Prosody Constraint (CPC) to encourage distinct prosody patterns for different emotions. The resulting model is trained on multi-speaker emotional corpora (LibriTTS, EmoV-DB, VCTK) with a combined objective that includes standard spectrogram reconstruction and variance prediction losses alongside our causal losses. In evaluations on expressive speech synthesis, our method achieves significantly improved prosody manipulation and emotion rendering, with higher mean opinion scores (MOS) and emotion accuracy than baseline FastSpeech2 variants. We also observe better intelligibility (low WER) and speaker consistency when transferring emotions across speakers. Extensive ablations confirm that the causal objectives successfully separate prosody attribution, yielding an interpretable model that allows controlled counterfactual prosody editing (e.g. "same utterance, different emotion") without compromising naturalness. We discuss the implications for identifiability in prosody modeling and outline limitations such as the assumption that emotion effects are fully captured by pitch, duration, and energy. Our work demonstrates how integrating causal learning principles into TTS can improve controllability and expressiveness in generated speech.

Suvendu Sekhar Mohanty

Arlington, Virginia, USA

TTS Synthesis Speech Prosody Controllable Speech Generation Emotional Speech Synthesis

Mar 11, 2026

When Fine-Tuning Fails and when it Generalises: Role of Data Diversity and Mixed Training in LLM-based TTS

Large language models are increasingly adopted as semantic backbones for neural text-to-speech systems. However, frozen LLM representations are insufficient for modeling speaker specific acoustic and perceptual characteristics. Our experiments involving fine tuning of the Language Model backbone of TTS show promise in improving the voice consistency and Signal to Noise ratio SNR in voice cloning task. Across multiple speakers LoRA finetuning consistently outperforms the non-finetuned base Qwen-0.5B model across three complementary dimensions of speech quality. First, perceptual quality improves significantly with DNS-MOS gains of up to 0.42 points for speakers whose training data exhibits sufficient acoustic variability. Second, speaker fidelity improves for all evaluated speakers with consistent increases in voice similarity indicating that LoRA effectively adapts speaker identity representations without degrading linguistic modeling. Third, signal level quality improves in most cases with signal to noise ratio increasing by as much as 34 percent. Crucially these improvements are strongly governed by the characteristics of the training data. Speakers with high variability in acoustic energy and perceptual quality achieve simultaneous gains in DNS-MOS voice similarity and SNR. Overall this work establishes that LoRA finetuning is not merely a parameter efficient optimization technique but an effective mechanism for better speaker level adaptation in compact LLM-based TTS systems. When supported by sufficiently diverse training data LoRA adapted Qwen-0.5B consistently surpasses its frozen base model in perceptual quality speaker similarity with low latency using GGUF model hosted in quantized form.

Anupam Purwar, Aditya Choudhary

Sprinklr AI Gurugram, India

TTS Synthesis Text-to-Speech LLM Fine-Tuning

Mar 9, 2026

Fish Audio S2 Technical Report

We introduce Fish Audio S2, an open-sourced text-to-speech system featuring multi-speaker, multi-turn generation, and, most importantly, instruction-following control via natural-language descriptions. To scale training, we develop a multi-stage training recipe together with a staged data pipeline covering video captioning and speech captioning, voice-quality assessment, and reward modeling. To push the frontier of open-source TTS, we release our model weights, fine-tuning code, and an SGLang-based inference engine. The inference engine is production-ready for streaming, achieving an RTF of 0.195 and a time-to-first-audio below 100 ms.Our code and weights are available on GitHub (https://github.com/fishaudio/fish-speech) and Hugging Face (https://huggingface.co/fishaudio/s2-pro). We highly encourage readers to visit https://fish.audio to try custom voices.

Shijia Liao, Yuxuan Wang, Songting Liu +11

Multi-Speaker TTS TTS Synthesis Controllable Speech Generation Streaming TTS Synthesis

Mar 8, 2026

Speech Generation Speaker Poisoning: Capability Erasure in Zero-Shot Text-to-Speech

Recent zero-shot Text-to-Speech (TTS) systems can clone previously unseen voices from only a few seconds of audio. We formulate Speech Generation Speaker Poisoning (SGSP), a task that seeks to prevent a model from synthesizing targeted speaker identities while maintaining performance on all other speakers. Unlike conventional machine unlearning, removing training examples is insufficient because modern zero-shot TTS systems can reconstruct identities through learned speaker representations and strong generalization capabilities. We evaluate both inference-time filtering and parameter-modification approaches across settings involving 1, 15, and 100 forget speakers, focusing primarily on speakers seen during training, which we show are harder to suppress than unseen speakers. To characterize the trade-off between utility and privacy, we introduce an evaluation framework based on AUC analysis and a proposed metric, Forget Set Similarity (FSSIM). Our results demonstrate effective speaker suppression for up to 15 forget speakers while revealing that worst-case identity leakage (Max-FSSIM) remains unresolved at multi-speaker scale - establishing this as an open challenge for future work. Together, our work establishes targeted speaker poisoning as a task for zero-shot TTS and, using StyleTTS2 as an initial testbed, provides methods and evaluation protocols for future research, with code and model weights.

Thanathai Lertpetchpun, Thanapat Trachu, Sai Praneeth Karimireddy +1

Signal Analysis and Interpretation Laboratory, University of Southern California · Thomas Lord Department of Computer Science, University of Southern California

TTS Synthesis Zero-Shot TTS Text-to-Speech Voice Cloning

Mar 8, 2026

Learning-free L2-Accented Speech Generation using Phonological Rules

Accent plays a crucial role in speaker identity and inclusivity in speech technologies. Existing accented text-to-speech (TTS) systems either require large-scale accented datasets or lack fine-grained phoneme-level controllability. We propose a accented TTS framework that combines phonological rules with a multilingual TTS model. The rules are applied to phoneme sequences to transform accent at the phoneme level while preserving intelligibility. The method requires no accented training data and enables explicit phoneme-level accent manipulation. We design rule sets for Spanish- and Indian-accented English, modeling systematic differences in consonants, vowels, and syllable structure arising from phonotactic constraints. We analyze the trade-off between phoneme-level duration alignment and accent as realized in speech timing. Experimental results demonstrate effective accent shift while maintaining speech quality.

Thanathai Lertpetchpun, Yoonjeong Lee, Jihwan Lee +3

Signal Analysis and Interpretation Lab, University of Southern California, USA · Department of Linguistics, University of Southern California

Mar 8, 2026

Accent Vector: Controllable Accent Manipulation for Multilingual TTS Without Accented Data

Accent is an integral part of society, reflecting multiculturalism and shaping how individuals express identity. The majority of English speakers are non-native (L2) speakers, yet current Text-To-Speech (TTS) systems primarily model American-accented English due limited accented data. We propose Accent Vector, a controllable representation that enables accent manipulation in multilingual TTS without requiring accented training data. Accent Vector is derived by fine-tuning a TTS system on native speech of a different language (i.e. non-English) and computing task vectors capturing accent characteristics (i.e. in English). By scaling and interpolating the vector, we achieve fine-grained control over accent strength and generate mixed-accent speech. In addition, it generalizes beyond English, enabling accent control across multiple languages. Objective and human evaluations confirm the effectiveness of Accent Vector for fine-grained and compositional accent control.

Thanathai Lertpetchpun, Thanapat Trachu, Jihwan Lee +3

Signal Analysis and Interpretation Lab, University of Southern California, USA · Thomas Lord Department of Computer Science, University of Southern California, USA · Department of Linguistics, University of Southern California

Multilingual TTS Synthesis TTS Synthesis Controllable Speech Generation

Mar 8, 2026

Bolbosh: Script-Aware Flow Matching for Kashmiri Text-to-Speech

Kashmiri is spoken by around 7 million people but remains critically underserved in speech technology, despite its official status and rich linguistic heritage. The lack of robust Text-to-Speech (TTS) systems limits digital accessibility and inclusive human-computer interaction for native speakers. In this work, we present the first dedicated open-source neural TTS system designed for Kashmiri. We show that zero-shot multilingual baselines trained for Indic languages fail to produce intelligible speech, achieving a Mean Opinion Score (MOS) of only 1.86, largely due to inadequate modeling of Perso-Arabic diacritics and language-specific phonotactics. To address these limitations, we propose Bolbosh, a supervised cross-lingual adaptation strategy based on Optimal Transport Conditional Flow Matching (OT-CFM) within the Matcha-TTS framework. This enables stable alignment under limited paired data. We further introduce a three-stage acoustic enhancement pipeline consisting of dereverberation, silence trimming, and loudness normalization to unify heterogeneous speech sources and stabilize alignment learning. The model vocabulary is expanded to explicitly encode Kashmiri graphemes, preserving fine-grained vowel distinctions. Our system achieves a MOS of 3.63 and a Mel-Cepstral Distortion (MCD) of 3.73, substantially outperforming multilingual baselines and establishing a new benchmark for Kashmiri speech synthesis. Our results demonstrate that script-aware and supervised flow-based adaptation are critical for low-resource TTS in diacritic-sensitive languages. Code and data are available at: https://github.com/gaash-lab/Bolbosh.

Tajamul Ashraf, Burhaan Rasheed Zargar, Saeed Abdul Muizz +5

King Abdullah University of Science and Technology (KAUST) · Gaash Lab, National Institute of Technology Srinagar · Department of Linguistics, University of Kashmir.

TTS Synthesis Low-Resource TTS Synthesis Low-Resource Language Processing

Mar 7, 2026

The Talking Robot: Distortion-Robust Acoustic Models for Robot-Robot Communication

We present Artoo, a learned acoustic communication system for robots that replaces hand-designed signal processing with end-to-end co-trained neural networks. Our system pairs a lightweight text-to-speech (TTS) transmitter (1.18M parameters) with a conformer-based automatic speech recognition (ASR) receiver (938K parameters), jointly optimized through a differentiable channel. Unlike human speech, robot-to-robot communication is paralinguistics-free: the system need not preserve timbre, prosody, or naturalness, only maximize decoding accuracy under channel distortion. Through a three-phase co-training curriculum, the TTS transmitter learns to produce distortion-robust acoustic encodings that surpass the baseline under noise, achieving 8.3% CER at 0 dB SNR. The entire system requires only 2.1M parameters (8.4 MB) and runs in under 13 ms end-to-end on a CPU, making it suitable for deployment on resource-constrained robotic platforms.

Hanlong Li, Karishma Kamalahasan, Jiahui Li +2

Institute of Science Tokyo · Georgia Institute of Technology

Robust ASR Automatic Speech Recognition Multi-Robot Systems TTS Synthesis

Mar 6, 2026

Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input

Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model is adapted to learn early stopping at specified content boundaries when provided with limited future text. During inference, a sliding-window prompt carries forward previous text and speech tokens, ensuring bounded context and seamless concatenation. Evaluations show our method outperforms CosyVoice-Style interleaved baseline in both short and long-form scenarios. In long-text synthesis, especially, it achieves a 66.2% absolute reduction in word error rate (from 71.0% to 4.8%) and increases speaker and emotion similarity by 16.1% and 1.5% relatively, offering a robust solution for streaming TTS with incremental text.

Changsong Liu, Tianrui Wang, Ye Ni +2

Nanyang Technological University, Singapore · Tianjin University, China · Southeast University, China

Long-Form TTS Synthesis TTS Synthesis Streaming TTS Synthesis Speech Language Models Speech Prosody

Mar 5, 2026

MSpoofTTS: Multi-Resolution Spoof-Guided Inference for Discrete Speech Synthesis

Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference optimization or retraining, we propose MSpoof-TTS, a training-free inference framework that improves zero-shot synthesis through multi-resolution spoof guidance. We introduce a Multi-Resolution Token-based Spoof Detection framework that evaluates codec sequences at different temporal granularities to detect locally inconsistent or unnatural patterns. We then integrate the spoof detectors into a hierarchical decoding strategy, progressively pruning low-quality candidates and re-ranking hypotheses. This discriminator-guided generation enhances robustness without modifying model parameters. Experiments validate the effectiveness of our framework for robust and high-quality codec-based speech generation. Audio samples and code are available.

Junchuan Zhao, Minh Duc Vu, Ye Wang

School of Computing, National University of Singapore, Singapore · Department of Statistics & Data Science, National University of Singapore, Singapore

TTS Synthesis Zero-Shot TTS

Mar 4, 2026

ZeSTA: Zero-Shot TTS Augmentation with Domain-Conditioned Training for Data-Efficient Personalized Speech Synthesis

We investigate the use of zero-shot text-to-speech (ZS-TTS) as a data augmentation source for low-resource personalized speech synthesis. While synthetic augmentation can provide linguistically rich and phonetically diverse speech, naively mixing large amounts of synthetic speech with limited real recordings often leads to speaker similarity degradation during fine-tuning. To address this issue, we propose ZeSTA, a simple domain-conditioned training framework that distinguishes real and synthetic speech via a lightweight domain embedding, combined with real-data oversampling to stabilize adaptation under extremely limited target data, without modifying the base architecture. Experiments on LibriTTS and an in-house dataset with two ZS-TTS sources demonstrate that our approach improves speaker similarity over naive synthetic augmentation while preserving intelligibility and perceptual quality. Audio samples are available on our web page.

Youngwon Choi, Jinwoo Oh, Hwayeon Kim +1

Maum AI Inc., Republic of Korea · Humelo Inc., Republic of Korea

Personalized Speech Recognition TTS Synthesis Low-Resource TTS Synthesis Synthetic Data Augmentation

Mar 2, 2026

More Data, Fewer Diacritics: Scaling Arabic TTS

Arabic Text-to-Speech (TTS) research has been hindered by the availability of both publicly available training data and accurate Arabic diacritization models. In this paper, we address the limitation by exploring Arabic TTS training on large automatically annotated data. Namely, we built a robust pipeline for collecting Arabic recordings and processing them automatically using voice activity detection, speech recognition, automatic diacritization, and noise filtering, resulting in around 4,000 hours of Arabic TTS training data. We then trained several robust TTS models with voice cloning using varying amounts of data, namely 100, 1,000, and 4,000 hours with and without diacritization. We show that though models trained on diacritized data are generally better, larger amounts of training data compensate for the lack of diacritics to a significant degree. We plan to release a public Arabic TTS model that works without the need for diacritization.

Ahmed Musleh, Yifan Zhang, Kareem Darwish

QCRI, HBKU, Qatar

TTS Synthesis Low-Resource TTS Synthesis Speech Corpus Construction

Mar 2, 2026

End-to-End Simultaneous Dysarthric Speech Reconstruction with Frame-Level Adaptor and Multiple Wait-k Knowledge Distillation

Dysarthric speech reconstruction (DSR) typically employs a cascaded system that combines automatic speech recognition (ASR) and sentence-level text-to-speech (TTS) to convert dysarthric speech into normally-prosodied speech. However, dysarthric individuals often speak more slowly, leading to excessively long response times in such systems, rendering them impractical in long-speech scenarios. Cascaded DSR systems based on streaming ASR and incremental TTS can help reduce latency. However, patients with differing dysarthria severity exhibit substantial pronunciation variability for the same text, resulting in poor robustness of ASR and limiting the intelligibility of reconstructed speech. In addition, incremental TTS suffers from poor prosodic feature prediction due to a limited receptive field. In this study, we propose an end-to-end simultaneous DSR system with two key innovations: 1) A frame-level adaptor module is introduced to bridge ASR and TTS. By employing explicit-implicit semantic information fusion and joint module training, it enhances the error tolerance of TTS to ASR outputs. 2) A multiple wait-k autoregressive TTS module is designed to mitigate prosodic degradation via multi-view knowledge distillation. Our system has an average response time of 1.03 seconds on Tesla A100, with an average real-time factor (RTF) of 0.71. On the UASpeech dataset, it attains a mean opinion score (MOS) of 4.67 and demonstrates a 54.25% relative reduction in word error rate (WER) compared to the state-of-the-art. Our demo is available at: https://wflrz123.github.io/

Minghui Wu, Haitao Tang, Jiahuan Fan +2

University of Science and Technology of China, China · iFlytek Co., Ltd., China

Clinical Speech Processing TTS Synthesis

Mar 2, 2026

DARS: Dysarthria-Aware Rhythm-Style Synthesis for ASR Enhancement

Dysarthric speech exhibits abnormal prosody and significant speaker variability, presenting persistent challenges for automatic speech recognition (ASR). While text-to-speech (TTS)-based data augmentation has shown potential, existing methods often fail to accurately model the pathological rhythm and acoustic style of dysarthric speech. To address this, we propose DARS, a dysarthria-aware rhythm-style synthesis framework based on the Matcha-TTS architecture. DARS incorporates a multi-stage rhythm predictor optimized by contrastive preferences between normal and dysarthric speech, along with a dysarthric-style conditional flow matching mechanism, jointly enhancing temporal rhythm reconstruction and pathological acoustic style simulation. Experiments on the TORGO dataset demonstrate that DARS achieves a Mean Cepstral Distortion (MCD) of 4.29, closely approximating real dysarthric speech. Adapting a Whisper-based ASR system with synthetic dysarthric speech from DARS achieves a 54.22% relative reduction in word error rate (WER) compared to state-of-the-art methods, demonstrating the framework's effectiveness in enhancing recognition performance.

Minghui Wu, Xueling Liu, Jiahuan Fan +3

University of Science and Technology of China, China · iFlytek Co., Ltd., China · Huawei Technology, China

Synthetic Data Augmentation for Speech Recognition TTS Synthesis Dysarthric Speech Recognition

Feb 26, 2026

TADA: A Generative Framework for Speech Modeling via Text-Acoustic Dual Alignment

Modern Text-to-Speech (TTS) systems increasingly leverage Large Language Model (LLM) architectures to achieve scalable, high-fidelity, zero-shot generation. However, these systems typically rely on fixed-frame-rate acoustic tokenization, resulting in speech sequences that are significantly longer than, and asynchronous with their corresponding text. Beyond computational inefficiency, this sequence length disparity often triggers hallucinations in TTS and amplifies the modality gap in spoken language modeling (SLM). In this paper, we propose a novel tokenization scheme that establishes one-to-one synchronization between continuous acoustic features and text tokens, enabling unified, single-stream modeling within an LLM. We demonstrate that these synchronous tokens maintain high-fidelity audio reconstruction and can be effectively modeled in a latent space by a large language model with a flow matching head. Moreover, the ability to seamlessly toggle speech modality within the context enables text-only guidance--a technique that blends logits from text-only and text-speech modes to flexibly bridge the gap toward text-only LLM intelligence. Experimental results indicate that our approach achieves performance competitive with state-of-the-art TTS and SLM systems while virtually eliminating content hallucinations and preserving linguistic integrity, all at a significantly reduced inference cost.

Trung Dang, Sharath Rao, Ananya Gupta +6

Hume AI, USA · Dartmouth College, USA

TTS Synthesis Speech Processing Speech Language Models

Feb 23, 2026

CTC-TTS: LLM-based dual-streaming text-to-speech with CTC alignment

Large-language-model (LLM)-based text-to-speech (TTS) systems can generate natural speech, but most are not designed for low-latency dual-streaming synthesis. High-quality dual-streaming TTS depends on accurate text--speech alignment and well-designed training sequences that balance synthesis quality and latency. Prior work often relies on GMM-HMM based forced-alignment toolkits (e.g., MFA), which are pipeline-heavy and less flexible than neural aligners; fixed-ratio interleaving of text and speech tokens struggles to capture text--speech alignment regularities. We propose CTC-TTS, which replaces MFA with a CTC based aligner and introduces a bi-word based interleaving strategy. Two variants are designed: CTC-TTS-L (token concatenation along the sequence length) for higher quality and CTC-TTS-F (embedding stacking along the feature dimension) for lower latency. Experiments show that CTC-TTS outperforms fixed-ratio interleaving and MFA-based baselines on streaming synthesis and zero-shot tasks.

Hanwen Liu, Saierdaer Yusuyin, Hao Huang +1

School of Computer Science and Technology, Xinjiang University, China · Speech Processing and Machine Intelligence (SPMI) Lab, Tsinghua University, China

TTS Synthesis Streaming TTS Synthesis Speech Language Models

Feb 22, 2026

CosyAccent: Duration-Controllable Accent Normalization Using Source-Synthesis Training Data

Accent normalization (AN) systems often struggle with unnatural outputs and undesired content distortion, stemming from both suboptimal training data and rigid duration modeling. In this paper, we propose a "source-synthesis" methodology for training data construction. By generating source L2 speech and using authentic native speech as the training target, our approach avoids learning from TTS artifacts and, crucially, requires no real L2 data in training. Alongside this data strategy, we introduce CosyAccent, a non-autoregressive model that resolves the trade-off between prosodic naturalness and duration control. CosyAccent implicitly models rhythm for flexibility yet offers explicit control over total output duration. Experiments show that, despite being trained without any real L2 speech, CosyAccent achieves significantly improved content preservation and superior naturalness compared to strong baselines trained on real-world data.

Qibing Bai, Shuhao Shi, Shuai Wang +3

SDS, The Chinese University of Hong Kong, Shenzhen, China · SRIBD, The Chinese University of Hong Kong, Shenzhen, China · Tencent Ethereal Audio Lab, Tencent, Shenzhen, China +3

Speech Processing Controllable Speech Generation TTS Synthesis

Feb 17, 2026

LLM-to-Speech: A Synthetic Data Pipeline for Training Dialectal Text-to-Speech Models

Despite the advances in neural text to speech (TTS), many Arabic dialectal varieties remain marginally addressed, with most resources concentrated on Modern Spoken Arabic (MSA) and Gulf dialects, leaving Egyptian Arabic -- the most widely understood Arabic dialect -- severely under-resourced. We address this gap by introducing NileTTS: 38 hours of transcribed speech from two speakers across diverse domains including medical, sales, and general conversations. We construct this dataset using a novel synthetic pipeline: large language models (LLM) generate Egyptian Arabic content, which is then converted to natural speech using audio synthesis tools, followed by automatic transcription and speaker diarization with manual quality verification. We fine-tune XTTS v2, a state-of-the-art multilingual TTS model, on our dataset and evaluate against the baseline model trained on other Arabic dialects. Our contributions include: (1) the first publicly available Egyptian Arabic TTS dataset, (2) a reproducible synthetic data generation pipeline for dialectal TTS, and (3) an open-source fine-tuned model. All resources are released to advance Egyptian Arabic speech synthesis research.

Ahmed Khaled Khamis, Hesham Ali

Georgia Institute of Technology · Nile University

TTS Synthesis Low-Resource TTS Synthesis Arabic Dialects Synthetic Data Generation

Feb 16, 2026

Probing Human Articulatory Constraints in End-to-End TTS with Reverse and Mismatched Speech-Text Directions

An end-to-end (e2e) text-to-speech (TTS) system is a deep architecture that learns to associate a text string with acoustic speech patterns from a curated dataset. It is expected that all aspects associated with speech production, such as phone duration, speaker characteristics, and intonation among other things are captured in the trained TTS model to enable the synthesized speech to be natural and intelligible. Human speech is complex, involving smooth transitions between articulatory configurations (ACs). Due to anatomical constraints, some ACs are challenging to mimic or transition between. In this paper, we experimentally study if the constraints imposed by human anatomy have an implication on training an e2e-TTS systems. We experiment with two e2e-TTS architectures, namely, Tacotron-2 an autoregressive model and VITS-TTS a non-autoregressive model. In this study, we build TTS systems using (a) forward text, forward speech (conventional, e2e-TTS), (b) reverse text, reverse speech (r-e2e-TTS), and (c) reverse text, forward speech (rtfs-e2e-TTS). Experiments demonstrate that e2e-TTS systems are purely data-driven. Interestingly, the generated speech by r-e2e-TTS systems exhibits better fidelity, better perceptual intelligibility, and better naturalness

Parth Khadse, Sunil Kumar Kopparapu

TCS Research, Tata Consultancy Services Limited, Mumbai, India

Jan 19, 2026

Zero-Shot Lombard Speech Synthesis with Controllable Style Embeddings

The Lombard effect plays a key role in natural communication, particularly in noisy environments or when addressing hearing-impaired listeners. We present a controllable text-to-speech (TTS) system capable of synthesizing Lombard-like speech in a zero-shot manner without requiring Lombard-specific training data. Our approach extends F5-TTS with a learned style embedding representation and analyzes the resulting latent space using principal component analysis (PCA) to identify directions associated with Lombard-related attributes. By manipulating these directions, we obtain interpretable control over vocal effort and articulation and generate speech at different Lombard levels. Experimental results show that the proposed method preserves speaker identity and naturalness, improves intelligibility under noisy conditions, and generalizes to previously unseen speakers. These findings demonstrate that style-embedding manipulation provides an effective and scalable framework for controllable zero-shot Lombard speech synthesis.

Seymanur Akti, Alexander Waibel

KIT Campus Transfer GmbH (KCT) · Karlsruhe Institute of Technology (KIT) · Carnegie Mellon University (CMU)

TTS Synthesis Zero-Shot TTS Controllable Speech Generation Speech Language Models

Jan 13, 2026

Decoding Order Matters in Autoregressive Speech Synthesis

Autoregressive speech synthesis often adopts a left-to-right order, yet generation order is a modelling choice. We investigate decoding order through masked diffusion framework, which progressively unmasks positions and allows arbitrary decoding orders during training and inference. By interpolating between identity and random permutations, we show that randomness in decoding order affects speech quality. We further compare fixed strategies, such as l2r and r2l with adaptive ones, such as Top-

K

, finding that fixed-order decoding, including the dominating left-to-right approach, is suboptimal, while adaptive decoding yields better performance. Finally, since masked diffusion requires discrete inputs, we quantise acoustic representations and find that even 1-bit quantisation can support reasonably high-quality speech.

Minghui Zhao, Anton Ragni

School of Computer Science, University of Sheffield, 211 Portobello, Sheffield S1 4DP, UK

Adaptive Inference TTS Synthesis Audio Diffusion Models Autoregressive Decoding

Nov 23, 2025

SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS

Automatic video dubbing aims to generate high-fidelity speech that is temporally aligned with visual content. However, existing methods still suffer from limited speech naturalness, insufficient audio-visual synchronization, and poor scalability beyond monolingual settings. To address these challenges, we propose SyncVoice, a simple and effective dubbing framework that lightly integrates a Text-Visual Fusion Module into a pretrained text-to-speech (TTS) system. This module aligns visual features with linguistic representations, enabling temporally synchronized speech synthesis without complex architectural redesign. Experiments on the LRS3 dataset show that SyncVoice achieves state-of-the-art performance in zero-shot dubbing. Further training on a large-scale bilingual audio-visual dataset improves vocal fidelity while preserving synchronization, yielding a single unified model for both Chinese and English dubbing.

Kaidi Wang, Yi He, Wenhao Guan +9

School of Informatics, Xiamen University, China · MiLM Plus, Xiaomi Inc., China · School of Electronic Science and Engineering, Xiamen University, China +1

TTS Synthesis Audio-Visual Synchronization Audio-Visual Alignment

Oct 28, 2025

Bayesian Speech Synthesizers Can Learn from Multiple Teachers

Text-to-speech (TTS) is a "one-to-many" problem: one text can be spoken in many valid ways, so its realizations form a distribution whose spread depends on the input. Most TTS models do not model this spread explicitly: they leave it implicit in the sampling process or fix it in advance. To model this distribution explicitly, we propose BELLE (Bayesian evidential learning with language modelling), which places a Bayesian prior over the mean and variance of each mel-spectrogram frame and predicts this prior from the input, while keeping the architecture and single-pass sampling of common continuous-valued autoregressive TTS models such as MELLE. Estimating this variance requires several recordings of each text, whereas standard TTS corpora provide one. We therefore construct two parallel-speech corpora: ParallelVox from real human recordings and LS+6TTS, which adds speech from six pre-trained TTS teachers to LibriSpeech (LS). Trained on these corpora, BELLE outperforms MELLE under the same training conditions, is competitive with larger TTS systems on the objective metrics of LibriSpeech test-clean, and supports streaming generation. Analyses of repeated human readings show that real speech has the properties the Bayesian prior assumes and that the variance predicted by BELLE follows the variation across these readings. Parallel speech improves BELLE, and synthetic parallel speech performs comparably to real parallel speech at the same volume and is far easier to scale.

Ziyang Zhang, Yifan Gao, Xuenan Xu +3

Tsinghua University · Shanghai Artificial Intelligence Laboratory.

TTS Synthesis Bayesian Neural Networks

Oct 12, 2025

ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis

Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, and a multi-dimensional quality assessment that covers both audio and Persian-specific text properties. The resulting release contains a 2,200-hour TTS-ready subset with 1.36 million aligned segments from 1,815 automatically inferred speaker IDs, making it more than 25 times larger than the largest previously available open Persian TTS dataset. To validate the corpus, we fine-tune XTTSv2, a zero-shot multilingual TTS model that operates directly on raw Persian text without phoneme representations. The resulting model achieves a naturalness MOS of 3.6/5 and a speaker-similarity MOS of 4.0/5. ParsVoice, its metadata, and the corpus-construction pipeline are publicly available on Hugging Face: https://huggingface.co/datasets/MohammadJRanjbar/ParsVoice and GitHub: https://github.com/MohammadJRanjbar/ParsVoice, supporting reproducible research on Persian speech synthesis and low-resource speech-language technologies.

Mohammad Javad Ranjbar Kalahroodi, Heshaam Faili, Azadeh Shakery

School of Electrical and Computer Engineering, University of Tehran, Iran · Institute for Research in Fundamental Sciences (IPM), Tehran, Iran

TTS Synthesis Multi-Speaker TTS Speech Processing Speech Corpus Construction