# Improved Consistency Training for Semi-Supervised Sequence-to-Sequence ASR via Speech Chain Reconstruction and Self-Transcribing

arXiv: https://arxiv.org/abs/2205.06963 · HTML: https://mlsanity.com/paper/2205.06963/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 31 references that are in the map.
- First posted on arXiv 14 May 2022.

## Builds on (most cited first, 21 of 21)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Temporal Ensembling for Semi-Supervised Learning](https://mlsanity.com/paper/1610.02242/) (2016)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learning](https://mlsanity.com/paper/1606.04586/) (2016)
- [SpeechBrain: A General-Purpose Speech Toolkit](https://mlsanity.com/paper/2106.04624/) (2021)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Learning with Pseudo-Ensembles](https://mlsanity.com/paper/1412.4864/) (2014)
- [End-to-End Attention-based Large Vocabulary Speech Recognition](https://mlsanity.com/paper/1508.04395/) (2015)
- [Improved Noisy Student Training for Automatic Speech Recognition](https://mlsanity.com/paper/2005.09629/) (2020)
- [Self-Training for End-to-End Speech Recognition](https://mlsanity.com/paper/1909.09116/) (2019)
- [ESPnet-TTS: Unified, Reproducible, and Integratable Open Source End-to-End Text-to-Speech Toolkit](https://mlsanity.com/paper/1910.10909/) (2019)
- [Listening while Speaking: Speech Chain by Deep Learning](https://mlsanity.com/paper/1707.04879/) (2017)
- [Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition](https://mlsanity.com/paper/2106.08922/) (2021)
- [Semi-Supervised Learning with Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/2007.13876/) (2020)
- [Contrastive Semi-supervised Learning for ASR](https://mlsanity.com/paper/2103.05149/) (2021)

## Built on by (most cited first, 2 of 2)

- [CR-CTC: Consistency regularization on CTC for improved speech recognition](https://mlsanity.com/paper/2410.05101/) (2024)
- [Filter and evolve: progressive pseudo label refining for semi-supervised automatic speech recognition](https://mlsanity.com/paper/2210.16318/) (2022)

## Abstract (arXiv)

Consistency regularization has recently been applied to semi-supervised sequence-to-sequence (S2S) automatic speech recognition (ASR). This principle encourages an ASR model to output similar predictions for the same input speech with different perturbations. The existing paradigm of semi-supervised S2S ASR utilizes SpecAugment as data augmentation and requires a static teacher model to produce pseudo transcripts for untranscribed speech. However, this paradigm fails to take full advantage of consistency regularization. First, the masking operations of SpecAugment may damage the linguistic contents of the speech, thus influencing the quality of pseudo labels. Second, S2S ASR requires both input speech and prefix tokens to make the next prediction. The static prefix tokens made by the offline teacher model cannot match dynamic pseudo labels during consistency training. In this work, we propose an improved consistency training paradigm of semi-supervised S2S ASR. We utilize speech chain reconstruction as the weak augmentation to generate high-quality pseudo labels. Moreover, we demonstrate that dynamic pseudo transcripts produced by the student ASR model benefit the consistency training. Experiments on LJSpeech and LibriSpeech corpora show that compared to supervised baselines, our improved paradigm achieves a 12.2% CER improvement in the single-speaker setting and 38.6% in the multi-speaker setting.