Text-to-Speech

Also known as TTS

Follow this topic Ask about this topic

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

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

Oct 19, 2026

SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTS

Expanding the vocabulary of conditional text-to-speech (TTS) models typically requires extensive fine-tuning with paired audio, creating a major bottleneck for low-resource and cross-lingual adaptation. To address this, we introduce SEAM, a zero-audio initialization method that constructs embeddings for unseen tokens from known subtokens. Unlike standard pooling strategies that ignore sequential structure, SEAM applies a spectral filter to preserve temporal phonetic order and uses closed-form ridge regression to align the new embeddings with the pretrained conditioning manifold. Across three languages and two TTS architectures, SEAM approaches or matches baseline performance using up to four times less training data, reducing sample complexity by 75% compared to random initialization and mean pooling. Our approach provides a lightweight, reproducible, and theoretically grounded solution for vocabulary expansion in low-resource speech synthesis.

Walaa Othman, Baher Mohammad, Stamatios Lefkimmiatis +1

ITMO University · SPC RAS · MWS AI

Text-to-Speech Low-Resource TTS Synthesis Multilingual TTS Synthesis

Oct 18, 2026

Does Expert Supervision Improve Text-to-Speech? An Empirical Study of Preference Optimization

Preference optimization promises to improve text-to-speech (TTS) systems by learning which speech outputs are better. External expert speech seems a natural source of preferred responses, especially when student generations contain errors. Yet demonstration quality does not establish whether the student can benefit from that supervision, or whether better target fitting will produce better speech. We examine this gap across two TTS students using real and synthetic expert speech, comparing preference objectives and direct versus bridge supervision while tracking fixed-sequence likelihoods and generation metrics. With expert supervision held fixed, objectives differ markedly in their sensitivity to preference-score scaling and the resulting generation quality. Likelihood diagnostics characterize these responses, but cannot establish their benefit: expert likelihood can increase while intelligibility worsens, or decrease while it improves. Bridge supervision highlights a distinction between mitigating degradation and improving the student: it can recover performance lost under direct training without consistently surpassing the pretrained base. Route benefits vary across objectives, students, and expert sources; neither route consistently dominates. Together, these findings distinguish demonstration quality, target fitting, and generated-speech quality as complementary criteria for assessing expert supervision.

Minh Duc Vu, Junchuan Zhao, Ye Wang

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

TTS Synthesis Text-to-Speech TTS Evaluation

Oct 7, 2026

Training-Free Instruction TTS Gender Bias Calibration Using Model-Adaptive Steering

Instruction text-to-speech (ITTS) systems systematically encode acoustic gender skews from descriptive style prompts, such as occupations or personas, even when demographic attributes are left unspecified. Calibrating the implicit gender distribution of the synthesized voices, across heterogeneous architectures and without model retraining or overriding explicit user prompts, is an open problem. In this work, we propose model-adaptive steering, a training-free bias calibration method that steers post-encoder conditioning representations using a group deviation vector paired with a coarse-to-fine strength search on a development set. A deterministic lexical gate bypasses intervention whenever explicit gender keywords are detected, preserving intended prompt semantics. Evaluated on a 12,800-prompt held-out benchmark across four ITTS models (three architectures), the proposed method reduces aggregate calibration error from 11.5--28.1 to 0.8--5.9 percentage points (e.g., shifting Parler-TTS Mini from 78.1% and PromptTTS++ from 27.3% female to 50.8--52.4%). Output rates stay within 0.9 pp across anchor set sizes at fixed operating points, while UTMOS decreases by at most 0.08 and WER degrades by at most 3.3 pp.

Kuan-Yu Chen, Yi-Cheng Lin, Jeng-Lin Li +1

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

Text-to-Speech TTS Synthesis Representation Steering

Oct 6, 2026

BanglaBox: A Phonetically-Balanced Corpus and Data-Efficient Foundation-Model Adaptation for Bangla Text-to-Speech with Zero-Shot Voice Cloning

We present a recipe for adapting English-pretrained autoregressive TTS foundation models to underrepresented languages, demonstrated on Bangladeshi Bangla. Existing Bangla TTS corpora are small and single-speaker, and to our knowledge no open zero-shot voice-cloning system is available for the Bangladeshi register. We contribute a phonetically- and gender-balanced two-tier Bangladeshi Bangla corpus balanced via a tiered Jensen-Shannon divergence objective over conjunct clusters (juktakkhor), together with three fine-tuning changes: a merge-consistent tokenizer extension, Bangla text normalization, and a prompt-masked dual-loss objective. These changes preserve zero-shot cloning across the language switch. Our BanglaEval protocol applies Wilcoxon signed-rank tests with Bonferroni correction over native-speaker ratings. BanglaBox attains near-natural Naturalness, outperforms commercial and open-source baselines on Naturalness, Speaker Similarity, and Clarity, and reaches speaker similarity comparable to prior few-shot results while using approximately 7x less Bangla fine-tuning audio. We further validate the recipe beyond our own test split using a seven-category stress set of difficult real-world text, the public BnTTS evaluation benchmarks, and naturally occurring Bangla that no language model wrote. All artifacts, including the corpus, weights, code, and complete evaluation materials, are released publicly and unconditionally.

Emtiaz Uddin Ahmed, Araf Mahmud, Sajib Hossain +3

Text-to-Speech Low-Resource TTS Synthesis Zero-Shot TTS Speech Foundation Models

Oct 2, 2026

Refinement Buys Intelligibility, Search Buys Identity: What Test-Time Compute Buys in Masked-Diffusion TTS

Diffusion language models for text-to-speech combine two forms of computation: model depth (parameters) and refinement steps (inference budget). We ask whether they scale equally across capabilities. We train 15 masked-diffusion codec TTS models varying depth (19-133M parameters, 3 seeds) on 2,000 hours of speech and sweep refinement steps T in [1,16] at inference, measuring zero-shot synthesis via ASR word error rate (intelligibility) and speaker verification (identity) on 174 held-out speakers. Against measured floors, refinement closes 86.2% of the intelligibility range but only 46.4% of the identity range - a 1.86x asymmetry robust across multiple error metrics. Retraining at 3x and 6x schedule attenuates but does not reverse this gap (1.84 to 1.36 to 1.23x), because intelligibility saturates with steps while identity continues improving. Best-of-K search recovers speaker identity where refinement fails, with 64.6-79.0% win rates across four independent encoders. Depth and steps are not interchangeable: separable B(d)B(T) fits significantly better (Delta AICc=+69.3) than substitution models. Analysis shows 62% of remaining identity deficit lies in the codec, not the generator. We conclude that refinement and depth target different bottlenecks and should be optimized separately.

Nityanand Mathur, Hamees Sayed, Ayush Pratap Singh

Work done outside of Blackstar Inc. · Work done at Smallest AI.

TTS Synthesis Text-to-Speech Test-Time Scaling Masked Diffusion Models Speech Generation Evaluation

Sep 30, 2026

Balalaika-Longform: A Russian Speech Corpus for Continuous Long-Form Text-to-Speech

Long-form text-to-speech must retain requested words over extended generations, yet sentence-level training and evaluation can hide omissions and early stops. We introduce Balalaika-Longform, an open Russian corpus of 189 hours in continuous units of 30 seconds to 15 minutes. Long units and matched short windows support fine-tuning comparisons on the same source recordings, and the accompanying evaluation retains every synthesis attempt. We fine-tune CosyVoice3, Qwen3-TTS, VoxCPM2 and F5-TTS on either view and test continuous synthesis on 50 text-voice pairs with voices unseen in fine-tuning, at about 75, 300 and 1,200 words. At 1,200 words, CosyVoice3 WER falls from 99.9% after short-window fine-tuning to 47.3% with long targets, and to 16.6% with punctuated, format-matched transcripts; paired intervals favor long targets for Qwen3-TTS and VoxCPM2, and by a small margin for F5-TTS, whose absolute WER stays above 90%. The results isolate the effect of training sequence length under a fixed continuous-generation protocol.

Nikita Vasiliev, Kirill Borodin, Vasilii Kudryavtsev +2

BitmanagerAI, Dubai, UAE · lab260, Yerevan, Armenia · MTUCI, Moscow, Russia

TTS Synthesis TTS Evaluation Long-Form TTS Synthesis Text-to-Speech Speech Corpus Construction

Sep 29, 2026

RAWD-TTS: Ratio-Free Reward Alignment for Discrete-Diffusion Voice Cloning

Zero-shot text-to-speech synthesizes new utterances in a speaker's voice from a short reference recording. Voice cloning requires accurate content and preserved speaker identity, but supervised acoustic-token prediction does not directly optimize these waveform-level properties. Reward-based post-training addresses this mismatch, but in discrete diffusion, token choices and reveal positions jointly define the sampling trajectory, complicating alignment. We introduce RAWD-TTS (Ratio-free Advantage-Weighted Denoising), which scores decoded samples with recognition and speaker rewards and uses group-relative advantages to weight masked-token reconstruction of those samples, without reverse-trajectory likelihoods or target audio. On 500 Russian CV3-Eval voice-cloning prompts, joint alignment reduces word error rate from 3.18% to 2.42% at the reward-selected checkpoint (24.0% relative) and to 2.58% at the final checkpoint (19.0%), while WavLM speaker cosine rises from 0.733 to 0.748 and 0.755. Controlled experiments characterize recognition-identity trade-offs and the effects of corruption count, group composition, and weighting.

Maxim Maslov, Kirill Borodin, Vasilii Kudryavtsev +2

lab260, Yerevan, Armenia · BitmanagerAI, Dubai, UAE · MTUCI, Moscow, Russia

Audio Diffusion Models Zero-Shot TTS Text-to-Speech Voice Cloning

Sep 29, 2026

DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors

Joint speech-gesture synthesis must coordinate two modalities despite limited paired data. Existing approaches often lack bidirectional interaction, have limited language coverage, or simplify body and finger representations. We present DualTrack, which couples pretrained speech and motion priors on a shared 12.5 Hz timeline. Causal adapters exchange previous-packet information, while current-state fusion coordinates the streams before they separately complete sixteen-codebook packets. We evaluate 43 BEAT2 recordings in four languages, with speakers held out from joint training and validation. On the shared English/Spanish inputs, without speech or motion prefixes, DualTrack achieves lower word error rate and full-motion Fréchet Gesture Distance, higher beat consistency and speech naturalness than the evaluated GELINA baseline.

Yuanzhuo Hu, Zehan Liu, Xiaoyi Qin +1

The Chinese University of Hong Kong, Shenzhen, China · X Square Robot

Human Motion Generation Co-Speech Gesture Generation Multimodal Fusion Text-to-Speech

Sep 28, 2026

InstCharVoice: Grounding Natural-Language Instructions for Character-Level Control in Text-to-Speech

Instruction-based text-to-speech (ITTS) systems enable natural-language control of expressive speech generation, but often offer limited transparency and fine-grained control over individual text units. Character-level controllable TTS systems provide explicit acoustic control, yet typically rely on user-specified acoustic attributes. To bridge this gap, we propose InstCharVoice, a unified framework that grounds natural-language instructions in character-level acoustic control. We first construct grounded instruction annotations on the WordVoice-5A-zh corpus using Qwen3-Omni. With this supervision, we train an autoregressive model to identify instruction-relevant characters and predict their acoustic attributes before generating the corresponding speech tokens. Keyword prediction and grounding-aware loss weighting help the model focus on instruction-relevant characters and attributes. Experiments show improved instruction following and keyword-level acoustic control over representative ITTS systems, with competitive speech naturalness and explicit character-level controllability. Audio samples are available at https://xxh333.github.io/instcharvoice-demo/.

Sihang Nie, Xueru Li, Xiaofen Xing +4

South China University of Technology · Huya Inc. · The Hongkong Polytechnic University

TTS Synthesis Language Model-Based Control Controllable Speech Generation Text-to-Speech Expressive Speech Synthesis

Sep 24, 2026

Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning

In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent analogy guidance (AAG), a training-free sampler term that subtracts an accent direction estimated from the model's own predictions for one synthetic voice rendered in both languages, so the voice cancels and only the accent remains. By a blind LLM accent judge on real dubbing data, reweighting classifier-free guidance between reference and text, and its variants, stay near one identity-accent trade-off curve; we score a method by its speaker similarity above that curve at equal accent (

Δ

SIM). Across four open TTS models AAG lies above the curve: on OmniVoice

Δ

SIM is +0.11 to +0.27 on three test sets (accent 3.51 to 4.28 on a 1-5 scale at speaker similarity 0.29, where reweighting keeps 0.02); MaskGCT and CosyVoice 2 also lie above their curves, and on F5-TTS it is more native than any reweighting setting. An LLM-free language-ID measure and a twelve-listener panel agree. A premise test and the reach of a model's own curve indicate in advance whether and roughly how much AAG can gain, predicting the one model where it gains nothing (X-Voice).

Yoomee Cho, Jisun Lee

ESTsoft, Seoul, Republic of Korea

TTS Synthesis Multilingual TTS Synthesis Zero-Shot TTS Text-to-Speech

Sep 13, 2026

Bridging Data, Reasoning, and Alignment: A Unified Framework for Context-Aware Instruction-Following TTS

The ISCSLP 2026 CoT-TTS Challenge requires TTS systems to generate Chain-of-Thought (CoT) reasoning from dialogue history before synthesizing contextually appropriate speech. While the official baseline establishes a unified architecture, it remains constrained by limited contextual comprehension, weak instruction fidelity, and suboptimal audio quality. We present a systematic optimization pipeline to address these limitations. First, we develop a data process framework that cleans raw data via FullSubNet denoising, Qwen3-ASR re-transcription, and Qwen3.5-35B-A3B-based history-CoT consistency analysis, while distilling 545K high-fidelity instruction samples using Qwen3-TTS and Seed-VC under strict quality filtration. Second, we propose a Context-Aware Direct Preference Optimization (CA-DPO) method. By employing a cascaded filtering strategy, ASR prescreening, LLM tournament ranking, and speaker similarity verification, we obtain high-confidence preference pairs that significantly enhance holistic ``Context

\rightarrow

CoT

\rightarrow

Speech'' consistency during DPO training. Third, we establish an evaluation method featuring a 500-sample test set and an LLM-as-Judge framework to independently assess reasoning and execution fidelity. Experiments demonstrate that our system significantly outperforms the baseline across all objective and subjective metrics, validating our data governance and alignment strategies.

Jingbin Hu, Luyu Wang, Wenjie Tian +7

Shenzhen Pimei Technology Co., Ltd., Guangdong, China · School of Intelligence Science and Technology, Nanjing University, Suzhou, China · State Key Laboratory of Novel Software Technology, Nanjing University, Nanjing, China

Text-to-Speech Speech Language Models Direct Preference Optimization

Sep 10, 2026

Post-Training Zero-Shot TTS for Fine-Grained Emotion and Duration Control via Natural Language

Audiobook narration, conversational agents, and audiovisual dubbing require fine-grained control over emotion and pacing within an utterance, yet many text-to-speech (TTS) systems remain limited to utterance-level conditioning. We propose a unified post-training framework for natural-language segment-level emotion and duration control. Supervised fine-tuning (SFT) establishes instruction following, while group relative policy optimization (GRPO) further improves control accuracy using emotion, duration, content, and speaker rewards. Without modifying the pretrained architecture or adding inference-time control modules, our method improves fine-grained controllability while preserving intelligibility and speaker identity, demonstrating post-training as an effective way to extend pretrained TTS models.

Lianru Gao, Yujie Guo, Yong Qin

TMCC, College of Computer Science, Nankai University, Tianjin, China

TTS Synthesis Zero-Shot TTS Controllable Speech Generation Text-to-Speech Emotional Speech Synthesis

Sep 2, 2026

Scalable Direction-Following TTS via Voice Impression-Guided Pseudo Triplet Construction

Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-following TTS, where a system generates a new utterance that reflects a given direction relative to a reference utterance while preserving speaker identity and linguistic content. A key challenge is the lack of training data capturing such relative modifications. To address this, we propose a scalable pseudo-triplet construction pipeline that generates~(reference utterance, direction text, modified utterance) triplets. It generates controlled style variations using an impression-controllable TTS model and uses an LLM to produce natural language directions from estimated impression differences. Experimental results demonstrate that pseudo-triplets alone enable stable speaker-preserving modification, and that combining pseudo and recorded data further improves direction alignment while maintaining speaker similarity. Audio examples are available on our demo page https://ntt-hilab-gensp.github.io/IS2026pseudo/

Kenichi Fujita, Yusuke Ijima

NTT, Inc., Japan

Expressive Speech Synthesis Text-to-Speech TTS Synthesis Synthetic Data Generation

Aug 29, 2026

Diagnose, Then Refine: A Closed-Loop TTS System with AudioLLM-Guided Correction

Current TTS systems typically rely on open-loop, single-pass generation and can produce sporadic local prosodic defects, such as misplaced stress, unnatural pauses, or flattened intonation, that utterance-level metrics often fail to expose. We present LoopTTS, a judge-guided Filter-Judge-Refiner framework for recovering low-quality TTS outputs diagnosed by an AudioLLM. Given an initial utterance from a base TTS model, an AudioLLM Judge identifies salient prosodic issues and generates structured refine instructions; a Refiner, our fine-grained instruction-following TTS model, then performs guided expressive re-synthesis conditioned on the initial utterance, target text, and instruction. To train the Refiner, we construct Refiner-DB, a 42K-example AudioLLM-annotated dataset with word-level prosodic weak supervision. Human evaluation on diagnosed low-quality utterances shows that LoopTTS can detect perceptually salient errors and correct them with the Refiner, outperforming raw generated audio and practical open-loop re-generation baselines in recovery quality. The Refiner also demonstrates stronger instruction-following ability for stress and pause control in targeted prosody modification.

Zeyang Song, Tianchi Liu, Tianrui Wang +3

National University of Singapore · Tencent · LIGHTSPEED +4

TTS Synthesis Text-to-Speech TTS Evaluation

Aug 11, 2026

ASR-Roundtrip Evaluation Can Mask Context- and Convention-Dependent Reading Errors in Chinese News TTS

ASR-roundtrip evaluation is widely used as a scalable proxy for text-to-speech (TTS) intelligibility, but it can produce false negatives for reading errors perceived by listeners. We study Chinese news TTS spans whose correct reading depends on context or domain conventions, such as sports scores, aircraft models, technical units, and membership names. In these cases, Raw TTS can choose a plausible but wrong reading while ASR transcribes the audio as the intended or surface-correct text. A targeted audit over 110 high-risk MiMo TTS cases, reported with a complete denominator, confirms 46 masked false negatives, 9 exposed TTS errors, and 55 cases with no Raw TTS error. A span-isolation diagnostic re-exposes 18/46 previously masked errors. A Raw-only CosyVoice audit on the same targeted pool confirms 51 masked cases. Across the 97 TTS-specific audio files labeled confirmed masked across the two audits, Qwen3-ASR surface-recovers 40 cases, whereas Paraformer does so in only 2. The results suggest that ASR-roundtrip is useful for screening but insufficient as standalone ground truth for Chinese news reading-risk evaluation.

Shijun Luo, Lizhi Wan

NetEase Cloud Music, Hangzhou, China

ASR Evaluation TTS Synthesis TTS Evaluation Speech Processing Text-to-Speech

Aug 10, 2026

Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions

Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Model (Audio-LLM) judges) are expected to reflect human perception, yet it is unclear how well they capture the distinct aspects of speech that listeners actually perceive. We deconstruct "naturalness" into a linguistically grounded annotation schema spanning 10 distinct perceptual dimensions, and use it to construct the first dimension-level meta-evaluation benchmark for TTS, comprising 860 utterances annotated by trained linguist raters. Results from benchmarking four MOS predictors and four Audio-LLM judges reveal that MOS predictors are more sensitive to acoustic signal-level properties at the prosodic and paralinguistic levels, while Audio-LLM judges show selective, prompt-dependent detection that favors word-level errors and does not generalize across all dimensions. Neither class reliably captures a breadth of linguistically structured, human-perceptible speech errors. Our dataset, annotation schema, and evaluation code are publicly released to support more targeted and interpretable TTS evaluation.

Oluwanifemi Bamgbose, Jash Shah, Simon Rosen +6

ServiceNow

Audio-Language Model Evaluation Human Preference Evaluation TTS Synthesis Speech Generation Evaluation TTS Evaluation Speech Quality Assessment+1

Aug 8, 2026

DialectS2S: End-to-End Speech Dialogue Modeling for Low-Resource Chinese Dialects

Current end-to-end speech dialogue models are primarily optimized for mainstream languages and remain limited in low-resource dialect scenarios due to the scarcity of dialect speech data. Moreover, during dialect adaptation, the semantic representation space of speech dialogue models continuously evolves, while conventional speech supervision remains unchanged, leading to semantic inconsistency between hidden representations and speech targets and degrading speech stability and naturalness. To address these issues, we propose DialectS2S, an end-to-end speech dialogue model for Chinese dialects. We first develop a scalable dialect speech dialogue synthesis pipeline for efficient data construction. We further introduce a two-stage post-training strategy with self-aligned speech supervision, which aligns the semantic content of speech supervision with the evolved semantic representations of the model to improve dialect speech generation quality. Experimental results show that DialectS2S consistently outperforms existing baselines across multiple Chinese dialects in speech dialogue, achieving substantial improvements in dialect consistency, response quality, and speech intelligibility. Our work provides an efficient and scalable solution for end-to-end speech dialogue modeling in low-resource dialect scenarios. To facilitate future research and practical applications, we fully open-source the DialectS2S framework, including model checkpoints, training datasets, and fine-tuning code.

Yi Shu, Tianyu Peng, Yingzhuo Deng +5

School of Artificial Intelligence, University of Chinese Academy of Sciences · Institute of Automation, Chinese Academy of Sciences · Wuhan AI Research +1

Spoken Dialogue Systems Speech Language Models Low-Resource Language Processing Text-to-Speech

Aug 3, 2026

Domain-Specific Evaluation of Text-to-Speech Systems: A Multi-Metric Benchmarking Study

Recent advances in neural text-to-speech (TTS) systems have substantially improved speech naturalness and intelligibility across many languages. However, comprehensive evaluation methodologies that jointly assess perceptual quality, speaker similarity, and acoustic fidelity across diverse speech domains remain limited, particularly for low-resource and underrepresented languages. This paper presents a reproducible, multi-metric benchmarking framework for systematic evaluation of modern TTS systems through domain-specific analysis. The proposed framework integrates complementary subjective and objective evaluation protocols and is demonstrated through a comprehensive case study on a representative low-resource language spanning four speech domains: Formal, Conversational, Literary/Storytelling, and Emotional. Four state-of-the-art TTS systems -- Indic-Parler-TTS, MMS-TTS, Microsoft Edge TTS, and Google Gemini TTS -- are evaluated using MUSHRA listening tests, ABX discrimination tests, speaker similarity scoring with Resemblyzer, and acoustic analyses based on mel-cepstral distortion (MCD) and F0 RMSE over 960 audio pairs. Results reveal substantial variation in TTS performance across speech domains, with emotional speech consistently presenting the greatest synthesis challenge (mean MCD 12.03 dB; mean F0 RMSE 889 cents), while conversational speech achieves the highest overall acoustic fidelity. Beyond the empirical findings, this work provides a reproducible evaluation framework, publicly releasing evaluation scripts, result tables, and executable Colab notebooks to support standardized benchmarking and future research on TTS evaluation for low-resource languages.

Ali Jafar, Amal Sarmad, Shifa Yousaf +1

FAST School of Computing, National University of Computer and Emerging Sciences (FAST-NUCES), Lahore, Punjab, Pakistan

Speech Generation Evaluation TTS Evaluation Speech Quality Assessment Low-Resource TTS Synthesis Text-to-Speech

Jul 23, 2026

Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs

Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDIA TensorRT and TensorRT-LLM. Faster IndexTTS-2 also enables streaming synthesis for latency-sensitive interactive applications, and batched inference across all components to maximize GPU utilization. Experiments on the Seed-TTS benchmark for both English and Chinese demonstrate up to 5.0

\times

speedup on the autoregressive GPT and 3.6

\times

end-to-end, with minimal degradation in word error rate, speaker similarity, and naturalness. Our methodology provides a practical reference for efficiently accelerating similar autoregressive speech models on GPUs.

Muyang Du, Shuang Yu, Junjie Lai

NVIDIA · Shanghai, China

TTS Synthesis Streaming TTS Synthesis Zero-Shot TTS Text-to-Speech

Jul 10, 2026

ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity. To address this issue, we propose ReGen, a hierarchical multi-prompt representation generation framework that jointly estimates multiple vector fields for both representations and data within a single diffusion model. We further introduce generalized flow matching (GFM) to improve the generalization of conditional flow matching (CFM). We validate ReGen on single-stage waveform diffusion models including neural audio codec and Wave-VAE. ReGen significantly improves waveform generation quality from highly compressed latent representations at 12.5 Hz. We also present ReGenVoice, a latent diffusion model (LDM)-based text-to-speech model that achieves strong speech intelligibility (WER) and speaker similarity (SIM) with a small dataset. Moreover, operating the LDM at 6.25 Hz with rich semantic and acoustic latent representation enables efficient training and sampling, requiring only 1 day of training on 4 GPUs and fast inference with an RTF of 0.08. Audio samples are available at https://regenvoice.github.io/demo/.

Sang-Hoon Lee, Ha-Yeong Choi

Department of Artificial Intelligence, Ajou University, Suwon, Korea · KT Corp., Seoul, Korea

Audio Representation Learning Latent Diffusion Models Conditional Flow Matching Audio Diffusion Models Text-to-Speech

Jul 5, 2026

Towards Digital Preservation of Efik: TTS for a Low-Resource African Language

Efik, a tonal language spoken by about 3 million second language speakers and 1.5 million native speakers in Southeastern Nigeria, remains underrepresented in speech synthesis research. We present the first documented end-to-end text-to-speech study for Efik, introducing a curated single speaker corpus of 2,632 utterances totaling three hours and a comparative evaluation of four neural models (VITS, MMS-TTS, SpeechT5, and Orpheus-TTS) under low resource conditions. Native speakers evaluated the systems using MOS, Nat-MOS, and A-MOS. MMS-TTS achieved the highest MOS of 3.80 +/- 0.63 and produced more stable long form speech, though tonal errors persisted. Other models showed greater tonal and prosodic inconsistencies. These results provide a reproducible baseline and highlight the need for larger corpora and tone aware modeling for tonal African languages.

Offiong Bassey Edet, Emmanuel Oyo-Ita, Archibong Okon Archibong +2

University of Cross River State, Nigeria · ML Collective · University of Calabar, Nigeria

TTS Synthesis Speech Generation Evaluation TTS Evaluation Low-Resource TTS Synthesis Low-Resource Language Processing Text-to-Speech+1

Jul 2, 2026

Towards a Phonology-Informed Evaluation of Multilingual TTS

Neural TTS systems can sound natural across languages, but naturalness does not guarantee the preservation of sound contrasts that distinguish words from their grammatical forms. Standard metrics like MOS do not test for this. We propose a classifier-based framework that audits TTS output against language-specific phonological patterns using human speech as a benchmark. Testing Assamese advanced tongue root (ATR) vowel harmony with Meta's MMS TTS, we show that a classifier trained on human speech transfers to synthesized speech with minimal loss. The faithfulness audit reveals that [+ATR] mid vowels are realized as [-ATR] in 1/3 tokens despite an underlying [+ATR] specification, a bias absent in human speech. At the word level, predicted ATR labels classify harmony more accurately than transcription labels, indicating a gap between intended and produced phonology. The framework offers task-specific diagnostics and generalizes to other phonological contrasts with measurable acoustic cues.

Sneha Ray Barman, Neeraj Kumar Sharma, Shakuntala Mahanta

Centre for Linguistic Science & Technology, IIT Guwahati · Mehta Family School for Data Science & Artificial Intelligence, IIT Guwahati · Department of Humanities & Social Sciences, IIT Guwahati

TTS Synthesis Speech Generation Evaluation TTS Evaluation Text-to-Speech

Jul 1, 2026

Enhancing Flow Matching with A Unified Guidance Framework for Efficient and Robust Speech Synthesis

Flow Matching (FM) has emerged as a powerful paradigm for speech generation but remains constrained by high inference latency and timbre leakage. To address these bottlenecks, we propose a unified guidance framework that enhances generation efficiency and robustness through two complementary strategies. On the data front, we introduce Data-guidance via heterogeneous augmentation, encouraging the model to disentangle linguistic content from acoustic residue. In parallel, we propose an enhanced Model-guidance mechanism that synergizes trajectory rectification with a novel intrinsic guidance objective. This approach distills conditional knowledge into network weights and straightens inference trajectory path, thereby eliminating Classifier-Free Guidance (CFG) overhead. Experiments demonstrate that our framework accelerates inference by nearly three times while effectively improving speaker similarity compared to state-of-the-art baselines.

Zuda Yu, Qianhui Xu, Ting Chen +5

Zuoyebang, China

Flow Matching Efficient Inference Text-to-Speech Inference-Time Guidance

Jun 30, 2026

LuxEmo: Expressive Text-to-Speech Corpus for Luxembourgish

State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories. LuxEmo is derived from Radio Télévision Luxembourg (RTL) youth broadcasts, using automated detection followed by human validation. We propose a semi-automatic curation workflow combining voice activity detection, denoising, language identification, LuxASR-based segmentation, automatic emotion prediction, lexical cues, and targeted human review. Additionally, we benchmark five expressive TTS systems covering German-based cross-lingual transfer, multilingual Luxembourgish support, Luxembourgish adaptation, and non-parametric prosody transfer. Performance is evaluated using both objective metrics and human evaluation.

Nina Hosseini-Kivanani, Sandipana Dowerah

Radio T´el´evisioun L¨etzebuerg (RTL) & University of Luxembourg · Esch-sur-Alzette, Luxembourg · Tallinn University of Technology +1

Speech Processing Low-Resource TTS Synthesis Low-Resource Language Processing Speech Corpus Construction Text-to-Speech Emotional Speech Synthesis

Jun 30, 2026

Is Natural Always Appropriate? Investigating Naturalness and Appropriateness Across Different Domains for TTS Evaluation

Text-to-speech (TTS) evaluation is an open challenge. While the primary target was "naturalness," recent fidelity gains shifted focus toward "appropriateness" and whether speech is correct for its context. In this work, we examine how perception changes when the expected downstream use varies. We measure the appropriateness and human-likeness of five SOTA TTS systems across five domains: AI assistant, reader, actor, animated character, and spontaneous speaker. Results show appropriateness varies across domains independently of naturalness. While systems shine at reading, expressive domains remain challenging, and optimizing for one can degrade others. Furthermore, naturalness scores tend to penalize stylized speech while rewarding spontaneity. Finally, our study also highlights blind spots in one-size-fits-all evaluation metrics across more expressive domains. We demonstrate that TTS performance is not "solved" but depends on the target domain, requiring context-aware evaluation.

Dominika Woszczyk, Andreas Triantafyllopoulos, Jura Miniota +2

Iconic, United Kingdom · Technische Universität München, Germany · KTH Royal Institute of Technology, Sweden +1

TTS Synthesis Speech Generation Evaluation TTS Evaluation Speech Quality Assessment Text-to-Speech

Jun 26, 2026

HPRO: Hierarchical Progressive Reward Optimization via Preference Extraction for Emotional Text-to-Speech

Recently, Large Language Model (LLM)-based Text-to-Speech (TTS) models have achieved remarkable naturalness. However, the standard Supervised Fine-Tuning paradigm often converges to statistically averaged prosody, limiting emotional expressiveness. While preference-driven optimization offers a promising alternative, existing approaches suffer from two structural mismatches: information conflict, where content and emotion in a shared latent space produce conflicting gradients, leading to reward hacking and semantic degradation; and scale gap, where sparse sentence-level rewards struggle to guide dense frame-level generation. To overcome these challenges, we propose HPRO, a hierarchical progressive reward optimization framework. Within HPRO, we introduce the HD-Emo codec as a novel differentiable reward model to mitigate the information conflict. It extracts speech into distinct content and style preference tokens, structurally isolating emotional optimization from semantic content. Building upon this structured preference space, HPRO bridges the scale gap by progressively aligning frame-, word- and sentence-level objectives. Experiments demonstrate that HPRO significantly enhances emotional expressiveness, while effectively preserving linguistic intelligibility. The code and audio samples are publicly available at https://xxh333.github.io/hpro-demo/.

Sihang Nie, Xiaofen Xing, Rui Xing +5

South China University of Technology, China · Huya Inc., China · Tongyi Fun Team, Alibaba Group, China +1

Reward Modeling Speech Prosody Text-to-Speech Emotional Speech Synthesis

Jun 25, 2026

Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean

Large pretrained text-to-speech (TTS) models sound almost human for well-resourced languages, but much worse for languages that are rare in their training data. We study this quality gap for Khmer and Korean using VoxCPM2, a 2.4B parameter, tokenizer-free TTS model that joins a MiniCPM-4 language-model backbone with a flow-matching diffusion decoder. We build one shared, language-tagged corpus of 25.5 hours after cleaning and adapt VoxCPM2 with a single Low-Rank Adaptation (LoRA) adapter, trained on both languages at once and added to both the language model and the decoder. The adapter is zero-initialized, so training starts exactly at the original zero-shot model. In native-speaker listening tests, the Khmer Mean Opinion Score (MOS) rises from 3.85 to 4.23 with the best adapter, rank 64. This gain is highly significant under a paired Wilcoxon test with p < 0.001, and it is achieved while training only 0.19 to 3.03 percent of the parameters. Two findings stand out. First, the training loss and human ratings disagree on the best rank. The loss is lowest at rank 128, but MOS peaks at rank 64. Second, the same adapter gives no significant gain for Korean, which the base model already covers well, and a high rank even hurts quality. This shows that adaptation helps mainly where the base model is truly weak.

Phannet Pov, Hyun Woo Park, Voneat Pen +3

Department of Big Data, Chungbuk National University, Cheongju, South Korea · Institute of Digital Research and Innovation, Cambodia Academy of Digital Technology, Phnom Penh, Cambodia · Department of Management Information Systems, Chungbuk National University, Cheongju, South Korea +1

Low-Resource TTS Synthesis Low-Resource Language Processing Text-to-Speech Parameter-Efficient Fine-Tuning

Jun 24, 2026

CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations

Accent conversion and controllability remain fundamental challenges in cross-lingual text-to-speech (TTS), particularly for low-resource and phonetically diverse Indic languages. While recent large language model (LLM)-based TTS systems exhibit strong cross-lingual generalization, they provide limited explicit control over accent characteristics and intensity. In this paper, we propose CrossAccentTTS, a framework that enables both accent control and conversion while preserving speaker identity. Specifically, we introduce an Accent Intensity Controller (AIC) that injects weighted language embeddings into the accent subspace, allowing smooth interpolation between accents and fine-grained modulation of accent strength at inference time. Experiments on the Indic Multilingual and L2-arctic datasets shows that CrossAccent-TTS achieves precise control of accent intensity, outperforming strong baselines in accent similarity and controllability by maintaining speaker similarity and naturalness.

Ram Annamdevula, Ankit Tatawat, Ashishkumar P. Gudmalwar +2

Media Analysis, Sony Research India

Disentangled Representation Learning TTS Synthesis Multilingual TTS Synthesis Controllable Speech Generation Text-to-Speech

Jun 24, 2026

Sarashina2.2-TTS: Tackling Kanji Polyphony in Japanese Speech Generation via Data Scaling and Targeted Data Synthesis

While large language model (LLM)-based text-to-speech (TTS) systems have achieved high-quality speech synthesis, most existing systems focus on English and Chinese. Japanese, however, remains under-explored, and its unique linguistic challenges, such as widespread context-dependent kanji polyphony, have yet to be adequately tackled. Here we introduce Sarashina2.2-TTS (https://github.com/sbintuitions/sarashina2.2-tts), a Japanese-centric LLM-TTS system that tackles these challenges through a dual approach: data strategy and evaluation methodology. First, we scale training to approximately 361k hours of speech, incorporating a balanced mix of Japanese and English data. Furthermore, we design a targeted data augmentation pipeline covering all 2,136 Joyo (regular-use) kanji designated by Japan's Agency for Cultural Affairs to efficiently address kanji polyphony disambiguation. Second, we introduce the Joyo Kanji Yomi Benchmark (https://github.com/sbintuitions/JoyoKanji-Yomi-Benchmark), covering all 2,136 Joyo kanji and their 4,378 readings. Alongside this benchmark, we propose Kana-CER, a metric that compares synthesized speech against reference readings in the kana space, eliminating orthographic variations to directly measure pronunciation correctness. Experiments demonstrate that our targeted data augmentation significantly improves reading accuracy. Overall, Sarashina2.2-TTS achieves state-of-the-art kanji-level reading accuracy and matches top baselines on general sentence-level pronunciation, while delivering the highest speaker similarity in zero-shot Japanese speech synthesis. Furthermore, cross-lingual evaluation reveals that Sarashina2.2-TTS is the only system that maintains stable Japanese pronunciation regardless of the prompt language, confirming that our balanced training approach improves cross-lingual robustness.

Lianbo Liu, Shiao Zhu, Kai Washizaki +10

SB Intuitions

TTS Synthesis Data Augmentation Zero-Shot TTS Text-to-Speech

Jun 23, 2026

CN-NewsTTS Bench: a target-level automatic benchmark for raw-input Chinese news TTS pronunciation

Chinese news text contains dense written forms such as scores, hyphenated model names, ranges, unit symbols, percentages, English abbreviations, and mixed Chinese-Latin-digit names. These forms are frequent in real listening workflows, and a text-to-speech (TTS) system can preserve the written string while changing the spoken meaning. We introduce CN-NewsTTS Bench v0.1, an open target-level benchmark for evaluating whether Chinese news TTS products pronounce such targets correctly from raw text, without user-side rules, LLM rewriting, SSML hints, or manual edits. The release contains a 200-record development set, an 800-record public test set, 992 public auto-evaluable targets, fixed transcripts from a three-ASR ensemble, an automatic target scorer, and initial results for seven product TTS systems. We additionally report ASR-route diagnostics, ASR-subset ablations, category-level results, confidence intervals, and provider configuration metadata. The best system reaches 0.879 strict accuracy, while several systems remain below 0.60.

Shijun Luo

NetEase Cloud Music, Hangzhou, China

Speech Generation Evaluation TTS Evaluation Text-to-Speech