@inproceedings{chi-etal-2021-align,
title = "Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment",
author = "Chi, Ethan A. and
Salazar, Julian and
Kirchhoff, Katrin",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.154/",
doi = "10.18653/v1/2021.naacl-main.154",
pages = "1920--1927",
abstract = "Non-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a non-autoregressive model. However, editing at the level of output sequences limits model flexibility. We instead propose \textit{iterative realignment}, which by refining latent alignments allows more flexible edits in fewer steps. Our model, Align-Refine, is an end-to-end Transformer which iteratively realigns connectionist temporal classification (CTC) alignments. On the WSJ dataset, Align-Refine matches an autoregressive baseline with a 14x decoding speedup; on LibriSpeech, we reach an LM-free test-other WER of 9.0{\%} (19{\%} relative improvement on comparable work) in three iterations. We release our code at \url{https://github.com/amazon-research/align-refine}."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chi-etal-2021-align">
<titleInfo>
<title>Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ethan</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Chi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Salazar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Kirchhoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Non-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a non-autoregressive model. However, editing at the level of output sequences limits model flexibility. We instead propose iterative realignment, which by refining latent alignments allows more flexible edits in fewer steps. Our model, Align-Refine, is an end-to-end Transformer which iteratively realigns connectionist temporal classification (CTC) alignments. On the WSJ dataset, Align-Refine matches an autoregressive baseline with a 14x decoding speedup; on LibriSpeech, we reach an LM-free test-other WER of 9.0% (19% relative improvement on comparable work) in three iterations. We release our code at https://github.com/amazon-research/align-refine.</abstract>
<identifier type="citekey">chi-etal-2021-align</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.154</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.154/</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>1920</start>
<end>1927</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment
%A Chi, Ethan A.
%A Salazar, Julian
%A Kirchhoff, Katrin
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F chi-etal-2021-align
%X Non-autoregressive encoder-decoder models greatly improve decoding speed over autoregressive models, at the expense of generation quality. To mitigate this, iterative decoding models repeatedly infill or refine the proposal of a non-autoregressive model. However, editing at the level of output sequences limits model flexibility. We instead propose iterative realignment, which by refining latent alignments allows more flexible edits in fewer steps. Our model, Align-Refine, is an end-to-end Transformer which iteratively realigns connectionist temporal classification (CTC) alignments. On the WSJ dataset, Align-Refine matches an autoregressive baseline with a 14x decoding speedup; on LibriSpeech, we reach an LM-free test-other WER of 9.0% (19% relative improvement on comparable work) in three iterations. We release our code at https://github.com/amazon-research/align-refine.
%R 10.18653/v1/2021.naacl-main.154
%U https://aclanthology.org/2021.naacl-main.154/
%U https://doi.org/10.18653/v1/2021.naacl-main.154
%P 1920-1927
Markdown (Informal)
[Align-Refine: Non-Autoregressive Speech Recognition via Iterative Realignment](https://aclanthology.org/2021.naacl-main.154/) (Chi et al., NAACL 2021)
ACL