paper-with-me

홈 › Papers

TokenChain: A Discrete Speech Chain via Semantic Token Modeling

2025-10-07 · Mingxuan Wang, Satoshi Nakamura 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.

📄 PDF Abstract BibTeX arXiv:2510.06201

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

A Comparative Study of Discrete Speech Tokens for Semantic-Related Tasks with Large Language Models

2024-11-13 · Dingdong Wang, Mingyu Cui, Dongchao Yang, Xueyuan Chen 외

With the rise of Speech Large Language Models (Speech LLMs), there has been growing interest in discrete speech tokens for their ability to integrate with text-based tokens seamlessly. Compared to most studies that focus…

DASB -- Discrete Audio and Speech Benchmark

2024-06-20 · Pooneh Mousavi, Luca Della Libera, Jarod Duret, Artem Ploujnikov 외

Discrete audio tokens have recently gained considerable attention for their potential to connect audio and language processing, enabling the creation of modern multimodal large language models. Ideal audio tokens must ef…

BenchmarkingEmotion Recognitionintent-classificationIntent Classification+7

High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model

2024-06-25 · Joun Yeop Lee, Myeonghun Jeong, Minchan Kim, Ji-Hyun Lee 외

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting mod…

Computational EfficiencyLanguage ModelingLanguage ModellingSpeech Synthesis+2

Recent Advances in Discrete Speech Tokens: A Review

2025-02-10 · Yiwei Guo, Zhihan Li, Hankun Wang, Bohan Li 외

The rapid advancement of speech generation technologies in the era of large language models (LLMs) has established discrete speech tokens as a foundational paradigm for speech representation. These tokens, characterized …

Language ModelingLanguage ModellingSpeech Tokenization

SELM: Speech Enhancement Using Discrete Tokens and Language Models

2023-12-15 · Ziqian Wang, Xinfa Zhu, Zihan Zhang, YuanJun Lv 외

Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech genera…

Self-Supervised LearningSpeech Enhancement