mlsanityData to 14 Oct 2026

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

arXiv 2301.02966 ↗First posted 8 Jan 2023cs.CL cs.LG eess.AScited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 8 Jan 2023.

Builds on

22 of 30 references.

References · 22

  1. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  2. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 804
  3. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
  4. 2018ESPnet: End-to-End Speech Processing Toolkitcited by 558
  5. 2015Listen, Attend and Spellcited by 543
  6. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  7. 2015Attention-Based Models for Speech Recognitioncited by 401
  8. 2019Self-Training for End-to-End Speech Recognitioncited by 129
  9. 2019Speech Recognition with Augmented Synthesized Speechcited by 60
  10. 2019ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkitcited by 60
  11. 2019Generating Synthetic Audio Data for Attention-Based Speech Recognition Systemscited by 47
  12. 2017Listening while Speaking: Speech Chain by Deep Learningcited by 46
10 more
  1. 2020MultiSpeech: Multi-Speaker Text to Speech with Transformercited by 42
  2. 2019Almost Unsupervised Text to Speech and Automatic Speech Recognitioncited by 41
  3. 2019Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutionscited by 27
  4. 2021fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkitcited by 24
  5. 2018Training Neural Speech Recognition Systems with Synthetic Speech Augmentationcited by 21
  6. 2021EAT: Enhanced ASR-TTS for Self-supervised Speech Recognitioncited by 13
  7. 2018Machine Speech Chain with One-shot Speaker Adaptationcited by 11
  8. 2022PaddleSpeech: An Easy-to-Use All-in-One Speech Toolkitcited by 9
  9. 2021Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architecturescited by 8
  10. 2021Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptationcited by 4

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1.

2 papers.

  1. 2023On Efficient Training of Large-Scale Deep Learning Models: A Literature Reviewcited by 26
  2. 2024Continual Learning in Machine Speech Chain Using Gradient Episodic Memorycited by 0