@inproceedings{zhao-etal-2022-redapt,
title = "{R}ed{A}pt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise",
author = "Zhao, Jinming and
Yang, Hao and
Haffari, Gholamreza and
Shareghi, Ehsan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.142",
doi = "10.18653/v1/2022.findings-emnlp.142",
pages = "1960--1967",
abstract = "Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive. To improve this, we present a novel Reducer Adaptor block, RedApt, that could be seamlessly integrated within any Transformer-based speech encoding architecture. Integrating the pretrained wav2vec 2 speech encoder with RedAptbrings 41{\%} speedup, 33{\%} memory reduction with 24{\%} fewer FLOPs at inference. To our positive surprise, our ST model with RedApt outperforms the SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhao-etal-2022-redapt">
<titleInfo>
<title>RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ehsan</namePart>
<namePart type="family">Shareghi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive. To improve this, we present a novel Reducer Adaptor block, RedApt, that could be seamlessly integrated within any Transformer-based speech encoding architecture. Integrating the pretrained wav2vec 2 speech encoder with RedAptbrings 41% speedup, 33% memory reduction with 24% fewer FLOPs at inference. To our positive surprise, our ST model with RedApt outperforms the SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.</abstract>
<identifier type="citekey">zhao-etal-2022-redapt</identifier>
<identifier type="doi">10.18653/v1/2022.findings-emnlp.142</identifier>
<location>
<url>https://aclanthology.org/2022.findings-emnlp.142</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1960</start>
<end>1967</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise
%A Zhao, Jinming
%A Yang, Hao
%A Haffari, Gholamreza
%A Shareghi, Ehsan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Findings of the Association for Computational Linguistics: EMNLP 2022
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F zhao-etal-2022-redapt
%X Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive. To improve this, we present a novel Reducer Adaptor block, RedApt, that could be seamlessly integrated within any Transformer-based speech encoding architecture. Integrating the pretrained wav2vec 2 speech encoder with RedAptbrings 41% speedup, 33% memory reduction with 24% fewer FLOPs at inference. To our positive surprise, our ST model with RedApt outperforms the SotA architecture by an average of 0.68 BLEU score on 8 language pairs from Must-C.
%R 10.18653/v1/2022.findings-emnlp.142
%U https://aclanthology.org/2022.findings-emnlp.142
%U https://doi.org/10.18653/v1/2022.findings-emnlp.142
%P 1960-1967
Markdown (Informal)
[RedApt: An Adaptor for wav2vec 2 EncodingFaster and Smaller Speech Translation without Quality Compromise](https://aclanthology.org/2022.findings-emnlp.142) (Zhao et al., Findings 2022)
ACL