TTS Synthesis

TTS: Text-to-Speech

Overview

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

CardsList

294 papers26 papers in the last four weeks, down 58% on the four weeks before. 0.2% of all new papers.

  1. ProTTS: End-to-End Prominence-aware Natural and Controllable Text-to-Speech via Automatic Word Stress Discovery

    Nov 15, 2026Sai Harshitha Aluru, Chiranjeevi YarraTTS SynthesisSpeech Processing

  2. Auditory-Feedback-Conditioned Flow TTS for Implicit Lombard Adaptation

    Nov 14, 2026Yunya Wang, Satoshi NakamuraTTS SynthesisExpressive Speech Synthesis

  3. Beyond Controllability: Speaker Diversity in Instruction-Guided Text-to-Speech

    Nov 14, 2026Yi-Cheng Lin, Jia-Kai Dong, Kuan-Yu Chen +5TTS SynthesisText-to-Speech

  4. ZONOS3-Mini Technical Report

    Nov 12, 2026Gabriel Clark, Sofian Mejjoute, George Close +1TTS SynthesisZero-Shot TTS

  5. Alania-2: Turkish text-to-speech with instant and fine-tuned voice cloning

    Nov 10, 2026Sezgin Saygili, Emre Kaplaner, Oncel Ozgul +1TTS SynthesisVoice Cloning

  6. WaveGen: Truly End-to-End Waveform Generation via Internal Spectral Trajectory Learning

    Nov 9, 2026Sang-Hoon Lee, Ha-Yeong ChoiTTS SynthesisAudio Diffusion Models

  7. BARS: Beat-Adaptive Rap Synthesis via Flow Matching

    Nov 9, 2026Taemin Cho, Hector Martel, Enyan KohTTS Synthesis

  8. Guidance at Pure Noise Erodes Speaker Similarity in Few-Step Token-Conditioned Flow-Matching TTS

    Nov 8, 2026Jaeho Lee, Han-Lim ChoiTTS SynthesisClassifier-Free Guidance

  9. M5-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi-Token Prediction

    Nov 6, 2026Wenhao Li, Jingbin Hu, Shengming Ling +20TTS SynthesisMultilingual TTS Synthesis

  10. Detector-Guided Vocoder Training for Adversarial Text-to-Speech Synthesis

    Nov 3, 2026Jiayan Cui, Davide Salvi, Paolo Bestagini +1TTS SynthesisAudio Deepfake Detection Robustness

  11. NepTTS-Bench: Native-Speaker Benchmarking and NepaliMOS for Nepali Text-to-Speech

    Oct 31, 2026Ashish Thapa, Rupak Ghimire, Lekhnath Sharma PathakTTS SynthesisTTS Evaluation

  12. Discovering Interpretable Acoustic Features in Autoregressive Voice-Cloning TTS Models

    Oct 29, 2026Anuj Diwan, David Harwath, Eunsol ChoiMechanistic InterpretabilityTTS Synthesis

  13. EmpDPO: Enabling Emphasis Control in TTS via Direct Preference Optimization

    Oct 29, 2026Haonan Chen, Yunyun Wang, Megan Wei +1TTS SynthesisMultilingual TTS Synthesis

  14. ImageTTS: Repurposing Pretrained Image Diffusion Transformers for Speech Synthesis

    Oct 26, 2026Hanchen Pei, Shujie Liu, Yayue Deng +4TTS SynthesisZero-Shot TTS

  15. LeanTTS: Efficient Full-Stack Bilingual TTS for Zero-Shot Cloning and Voice Customization

    Oct 25, 2026Yuheng Lu, Qiulin Li, Xi Wang +5TTS SynthesisZero-Shot TTS

  16. HeyGen Voice: Scene-Aware Voice Cloning for Talking Videos

    Oct 21, 2026Pavel Andreev, Andrei Gusev, Adithya Narayan +15Voice CloningTTS Synthesis

  17. LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS

    Oct 20, 2026Jie Liu, Junyu Zhou, Junhao Zhong +5TTS SynthesisCredit Assignment

  18. Steering intonational tunes in text-to-speech synthesis

    Oct 19, 2026Juan Pablo Vigneaux, Jennifer ColeTTS SynthesisSpeech Prosody

  19. MixiSpeech: Progressive State Distillation for One-Step Vietnamese TTS

    Oct 18, 2026Tran Quoc Bao Le, Binh Mai, Hung Dinh +2TTS SynthesisMulti-Speaker TTS

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

    Oct 18, 2026Minh Duc Vu, Junchuan Zhao, Ye WangTTS SynthesisText-to-Speech

  21. ShlokaDhara: A Multi-Speaker Sanskrit Speech Corpus for Learning Meter-Aware Prosody in Text-to-Recitation

    Oct 17, 2026Harshal Kausadikar, Onkar Kishor Susladkar, Prathmesh Santosh Choudhari +3Speech ProcessingTTS Synthesis

  22. Vocal-Tract Acoustics, Aerodynamics, and Overlap-and-Add Synthesis in DYNARTmo

    Oct 17, 2026Bernd J. KrögerControllable Speech GenerationTTS Synthesis