Self-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

by   Murali Karthick Baskar, et al.
Brno University of Technology

Sequence-to-sequence ASR models require large quantities of data to attain high performance. For this reason, there has been a recent surge in interest for self-supervised and supervised training in such models. This work builds upon recent results showing notable improvements in self-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 self-supervised loss combining an end-to-end differentiable ASR→TTS loss with a point estimate TTS→ASR 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 to reproduce the experiments.


EAT: Enhanced ASR-TTS for Self-supervised Speech Recognition

Self-supervised ASR-TTS models suffer in out-of-domain data conditions. ...

An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition

Self-supervised pretraining on speech data has achieved a lot of progres...

Cycle-consistency training for end-to-end speech recognition

This paper presents a method to train end-to-end automatic speech recogn...

Avoid Overthinking in Self-Supervised Models for Speech Recognition

Self-supervised learning (SSL) models reshaped our approach to speech, l...

MAESTRO: Matched Speech Text Representations through Modality Matching

We present Maestro, a self-supervised training method to unify represent...

Iterative pseudo-forced alignment by acoustic CTC loss for self-supervised ASR domain adaptation

High-quality data labeling from specific domains is costly and human tim...

Please sign up or login with your details

Forgot password? Click here to reset