mlsanityData to 7 Oct 2026

TokenChain: A Discrete Speech Chain via Semantic Token Modeling

arXiv 2510.06201 ↗First posted 7 Oct 2025eess.AS cs.AI cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

Machine Speech Chain, simulating the human perception-production loop, proves effective in jointly improving ASR and TTS. We propose TokenChain, a fully discrete speech chain coupling semantic-token ASR with a two-stage TTS: an autoregressive text-to-semantic model co-trained with ASR and a masked-generative semantic-to-acoustic model for synthesis only. End-to-end feedback across the text interface is enabled with straight-through argmax/Gumbel-Softmax and balanced with supervised ASR via dynamic weight averaging. Ablations examine optimal temperature schedules for in- and cross-domain transfer. Evaluation reveals TokenChain surpasses baseline accuracy 2-6 epochs earlier and yields 5-13% lower equal-epoch error with stable T2S on LibriSpeech, and reduces relative ASR WER by 56% and T2S WER by 31% on TED-LIUM with minimal forgetting, showing that chain learning remains effective with token interfaces and models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 28 references that are in the map. First posted on arXiv 7 Oct 2025.

Builds on

22 of 28 references.

References · 22

  1. 2023Llama 2: Open Foundation and Fine-Tuned Chat Modelscited by 12,865
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  3. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  4. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,708
  5. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  6. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  7. 2021SoundStream: An End-to-End Neural Audio Codeccited by 756
  8. 2022AudioLM: a Language Modeling Approach to Audio Generationcited by 611
  9. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 554
  10. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  11. 2024Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generationcited by 200
  12. 2024MaskGCT: Zero-Shot Text-to-Speech with Masked Generative Codec Transformercited by 159
10 more
  1. 2023SoundStorm: Efficient Parallel Audio Generationcited by 111
  2. 2023SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Modelscited by 85
  3. 2024Recent Advances in Speech Language Models: A Surveycited by 85
  4. 2024The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speechcited by 78
  5. 2017Listening while Speaking: Speech Chain by Deep Learningcited by 46
  6. 2025Recent Advances in Discrete Speech Tokens: A Reviewcited by 42
  7. 2023Amphion: An Open-Source Audio, Music and Speech Generation Toolkitcited by 25
  8. 2024Towards Controllable Speech Synthesis in the Era of Large Language Models: A Systematic Surveycited by 22
  9. 2018End-to-End Feedback Loss in Speech Chain Framework via Straight-Through Estimatorcited by 11
  10. 2021Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptationcited by 4

Built on by

Not cited yet.