SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain

Heli Qi, Sashi Novitasari, Andros Tjandra, Sakriani Sakti, Satoshi Nakamura
1/8/2023
cs.CLcs.LGeess.AS

No confident code implementation found for this paper.

Abstract

This paper introduces SpeeChain, an open-source Pytorch-based toolkit designed to develop the machine speech chain for large-scale use. This first release focuses on the TTS-to-ASR chain, a core component of the machine speech chain, that refers to the TTS data augmentation by unspoken text for ASR. To build an efficient pipeline for the large-scale TTS-to-ASR chain, we implement easy-to-use multi-GPU batch-level model inference, multi-dataloader batch generation, and on-the-fly data selection techniques. In this paper, we first explain the overall procedure of the TTS-to-ASR chain and the difficulties of each step. Then, we present a detailed ablation study on different types of unlabeled data, data filtering thresholds, batch composition, and real-synthetic data ratios. Our experimental results on train_clean_460 of LibriSpeech demonstrate that our TTS-to-ASR chain can significantly improve WER in a semi-supervised setting.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

TokenChain: A Discrete Speech Chain via Semantic Token Modeling

83% match2025

Hard-Synth: Synthesizing Diverse Hard Samples for ASR using Zero-Shot TTS and LLM

82% match2024

TouchTTS: An Embarrassingly Simple TTS Framework that Everyone Can Touch

81% match2024

Anatomy of Industrial Scale Multilingual ASR

81% match2024

A Self-Refining Framework for Enhancing ASR Using TTS-Synthesized Data

81% match2025

Generating Data with Text-to-Speech and Large-Language Models for Conversational Speech Recognition

81% match2024

Cite this paper

@article{qi2023speechain,
  title  = {SpeeChain: A Speech Toolkit for Large-Scale Machine Speech Chain},
  author = {Heli Qi and Sashi Novitasari and Andros Tjandra and Sakriani Sakti and Satoshi Nakamura},
  year   = {2023},
  eprint = {2301.02966},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2301.02966v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2301.02966.svg)](https://codeofpaper.com/paper/2301.02966)

Discussion