# Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

arXiv: https://arxiv.org/abs/1905.01152 · HTML: https://mlsanity.com/paper/1905.01152/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Apr 2019.

## Built on by (most cited first, 10 of 10)

- [Recent Advances in End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2111.01690/) (2021)
- [Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition](https://mlsanity.com/paper/2106.08922/) (2021)
- [fairseq S^2: A Scalable and Integrable Speech Synthesis Toolkit](https://mlsanity.com/paper/2109.06912/) (2021)
- [On Addressing Practical Challenges for RNN-Transducer](https://mlsanity.com/paper/2105.00858/) (2021)
- [Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition](https://mlsanity.com/paper/2101.06699/) (2021)
- [Internal Language Model Adaptation with Text-Only Data for End-to-End Speech Recognition](https://mlsanity.com/paper/2110.05354/) (2021)
- [EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition](https://mlsanity.com/paper/2104.07474/) (2021)
- [Comparing the Benefit of Synthetic Training Data for Various Automatic Speech Recognition Architectures](https://mlsanity.com/paper/2104.05379/) (2021)
- [Exploring Machine Speech Chain for Domain Adaptation and Few-Shot Speaker Adaptation](https://mlsanity.com/paper/2104.03815/) (2021)
- [Improving Semi-supervised End-to-end Automatic Speech Recognition using CycleGAN and Inter-domain Losses](https://mlsanity.com/paper/2210.11642/) (2022)

## Abstract (arXiv)

Sequence-to-sequence automatic speech recognition (ASR) models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for unsupervised and semi-supervised training in such models. This work builds upon recent results showing notable improvements in semi-supervised training using cycle-consistency and related techniques. Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models. In particular, this work proposes a new semi-supervised loss combining an end-to-end differentiable ASRrightarrowTTS loss with TTSrightarrowASR loss. The method is able to leverage both unpaired speech and text data to outperform recently proposed related techniques in terms of %WER. We provide extensive results analyzing the impact of data quantity and speech and text modalities and show consistent gains across WSJ and Librispeech corpora. Our code is provided in ESPnet to reproduce the experiments.