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

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F19%3APU134179" target="_blank" >RIV/00216305:26230/19:PU134179 - isvavai.cz</a>

Výsledek na webu

<a href="https://www.isca-speech.org/archive/Interspeech_2019/pdfs/3167.pdf" target="_blank" >https://www.isca-speech.org/archive/Interspeech_2019/pdfs/3167.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.21437/Interspeech.2019-3167" target="_blank" >10.21437/Interspeech.2019-3167</a>

Jazyk výsledku

angličtina

Název v původním jazyce

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

Popis výsledku v původním jazyce

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.

Název v anglickém jazyce

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

Popis výsledku anglicky

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.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/LQ1602" target="_blank" >LQ1602: IT4Innovations excellence in science</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

Proceedings of Interspeech

ISBN

—

ISSN

1990-9772

e-ISSN

—

Počet stran výsledku

5

Strana od-do

3790-3794

Název nakladatele

International Speech Communication Association

Místo vydání

Graz

Místo konání akce

INTERSPEECH 2019

Datum konání akce

15. 9. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—