Semi-supervised sequence-to-sequence ASR using unpaired speech and text

Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo, Takaaki Hori, Lukáš Burget, Jan Černocký

Research output: Contribution to journalConference articlepeer-review

32 Citations (Scopus)


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 ASR→TTS loss with 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 in ESPnet to reproduce the experiments.

Original languageEnglish
Pages (from-to)3790-3794
Number of pages5
JournalProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Publication statusPublished - 2019
Externally publishedYes
Event20th Annual Conference of the International Speech Communication Association: Crossroads of Speech and Language, INTERSPEECH 2019 - Graz, Austria
Duration: 2019 Sept 152019 Sept 19


  • ASR
  • Cycle consistency
  • End-to-end
  • Semi-supervised
  • Sequence-to-sequence
  • TTS
  • Unsupervised

ASJC Scopus subject areas

  • Language and Linguistics
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Modelling and Simulation


Dive into the research topics of 'Semi-supervised sequence-to-sequence ASR using unpaired speech and text'. Together they form a unique fingerprint.

Cite this