Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis
Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the pho...
Gespeichert in:
Veröffentlicht in: | arXiv.org 2022-03 |
---|---|
Hauptverfasser: | , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | |
container_start_page | |
container_title | arXiv.org |
container_volume | |
creator | Wang, Zexun Le, Yuquan Zhu, Yi Zhao, Yuming Feng, Mingchao Chen, Meng He, Xiaodong |
description | Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the phoneme sequence of speech can complement ASR hypothesis and enhance the robustness of SLU. This paper proposes a novel model with Cross Attention for SLU (denoted as CASLU). The cross attention block is devised to catch the fine-grained interactions between phoneme and word embeddings in order to make the joint representations catch the phonetic and semantic features of input simultaneously and for overcoming the ASR errors in downstream natural language understanding (NLU) tasks. Extensive experiments are conducted on three datasets, showing the effectiveness and competitiveness of our approach. Additionally, We also validate the universality of CASLU and prove its complementarity when combining with other robust SLU techniques. |
format | Article |
fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2642602929</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2642602929</sourcerecordid><originalsourceid>FETCH-proquest_journals_26426029293</originalsourceid><addsrcrecordid>eNqNy8EKglAQheFLEBTlOwy0DmxMq6VJ4aJFZK1DczLN5ppzL9HbJ9EDtDqL8389NUTPm02Xc8SBckQq13UxWKDve0NVr21Z5yUXcNCZFQNJo-_EsEu5sGlBcOKcWjEpf6PsDVGrRSA0htiUmiEj86JO7G-a6UGQ0NMSXwg6AmFygPjdaHMjKWWs-te0FnJ-O1KT7eYYxdOm1R0Sc660bbm7zhjMMXBxhSvvv-oDmptJTw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2642602929</pqid></control><display><type>article</type><title>Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis</title><source>Free E- Journals</source><creator>Wang, Zexun ; Le, Yuquan ; Zhu, Yi ; Zhao, Yuming ; Feng, Mingchao ; Chen, Meng ; He, Xiaodong</creator><creatorcontrib>Wang, Zexun ; Le, Yuquan ; Zhu, Yi ; Zhao, Yuming ; Feng, Mingchao ; Chen, Meng ; He, Xiaodong</creatorcontrib><description>Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the phoneme sequence of speech can complement ASR hypothesis and enhance the robustness of SLU. This paper proposes a novel model with Cross Attention for SLU (denoted as CASLU). The cross attention block is devised to catch the fine-grained interactions between phoneme and word embeddings in order to make the joint representations catch the phonetic and semantic features of input simultaneously and for overcoming the ASR errors in downstream natural language understanding (NLU) tasks. Extensive experiments are conducted on three datasets, showing the effectiveness and competitiveness of our approach. Additionally, We also validate the universality of CASLU and prove its complementarity when combining with other robust SLU techniques.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Automatic speech recognition ; Errors ; Hypotheses ; Phonemes ; Phonetics ; Robustness ; Voice recognition</subject><ispartof>arXiv.org, 2022-03</ispartof><rights>2022. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>780,784</link.rule.ids></links><search><creatorcontrib>Wang, Zexun</creatorcontrib><creatorcontrib>Le, Yuquan</creatorcontrib><creatorcontrib>Zhu, Yi</creatorcontrib><creatorcontrib>Zhao, Yuming</creatorcontrib><creatorcontrib>Feng, Mingchao</creatorcontrib><creatorcontrib>Chen, Meng</creatorcontrib><creatorcontrib>He, Xiaodong</creatorcontrib><title>Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis</title><title>arXiv.org</title><description>Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the phoneme sequence of speech can complement ASR hypothesis and enhance the robustness of SLU. This paper proposes a novel model with Cross Attention for SLU (denoted as CASLU). The cross attention block is devised to catch the fine-grained interactions between phoneme and word embeddings in order to make the joint representations catch the phonetic and semantic features of input simultaneously and for overcoming the ASR errors in downstream natural language understanding (NLU) tasks. Extensive experiments are conducted on three datasets, showing the effectiveness and competitiveness of our approach. Additionally, We also validate the universality of CASLU and prove its complementarity when combining with other robust SLU techniques.</description><subject>Automatic speech recognition</subject><subject>Errors</subject><subject>Hypotheses</subject><subject>Phonemes</subject><subject>Phonetics</subject><subject>Robustness</subject><subject>Voice recognition</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><recordid>eNqNy8EKglAQheFLEBTlOwy0DmxMq6VJ4aJFZK1DczLN5ppzL9HbJ9EDtDqL8389NUTPm02Xc8SBckQq13UxWKDve0NVr21Z5yUXcNCZFQNJo-_EsEu5sGlBcOKcWjEpf6PsDVGrRSA0htiUmiEj86JO7G-a6UGQ0NMSXwg6AmFygPjdaHMjKWWs-te0FnJ-O1KT7eYYxdOm1R0Sc660bbm7zhjMMXBxhSvvv-oDmptJTw</recordid><startdate>20220322</startdate><enddate>20220322</enddate><creator>Wang, Zexun</creator><creator>Le, Yuquan</creator><creator>Zhu, Yi</creator><creator>Zhao, Yuming</creator><creator>Feng, Mingchao</creator><creator>Chen, Meng</creator><creator>He, Xiaodong</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20220322</creationdate><title>Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis</title><author>Wang, Zexun ; Le, Yuquan ; Zhu, Yi ; Zhao, Yuming ; Feng, Mingchao ; Chen, Meng ; He, Xiaodong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26426029293</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Automatic speech recognition</topic><topic>Errors</topic><topic>Hypotheses</topic><topic>Phonemes</topic><topic>Phonetics</topic><topic>Robustness</topic><topic>Voice recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Wang, Zexun</creatorcontrib><creatorcontrib>Le, Yuquan</creatorcontrib><creatorcontrib>Zhu, Yi</creatorcontrib><creatorcontrib>Zhao, Yuming</creatorcontrib><creatorcontrib>Feng, Mingchao</creatorcontrib><creatorcontrib>Chen, Meng</creatorcontrib><creatorcontrib>He, Xiaodong</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wang, Zexun</au><au>Le, Yuquan</au><au>Zhu, Yi</au><au>Zhao, Yuming</au><au>Feng, Mingchao</au><au>Chen, Meng</au><au>He, Xiaodong</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis</atitle><jtitle>arXiv.org</jtitle><date>2022-03-22</date><risdate>2022</risdate><eissn>2331-8422</eissn><abstract>Building Spoken Language Understanding (SLU) robust to Automatic Speech Recognition (ASR) errors is an essential issue for various voice-enabled virtual assistants. Considering that most ASR errors are caused by phonetic confusion between similar-sounding expressions, intuitively, leveraging the phoneme sequence of speech can complement ASR hypothesis and enhance the robustness of SLU. This paper proposes a novel model with Cross Attention for SLU (denoted as CASLU). The cross attention block is devised to catch the fine-grained interactions between phoneme and word embeddings in order to make the joint representations catch the phonetic and semantic features of input simultaneously and for overcoming the ASR errors in downstream natural language understanding (NLU) tasks. Extensive experiments are conducted on three datasets, showing the effectiveness and competitiveness of our approach. Additionally, We also validate the universality of CASLU and prove its complementarity when combining with other robust SLU techniques.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | EISSN: 2331-8422 |
ispartof | arXiv.org, 2022-03 |
issn | 2331-8422 |
language | eng |
recordid | cdi_proquest_journals_2642602929 |
source | Free E- Journals |
subjects | Automatic speech recognition Errors Hypotheses Phonemes Phonetics Robustness Voice recognition |
title | Building Robust Spoken Language Understanding by Cross Attention between Phoneme Sequence and ASR Hypothesis |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-20T20%3A16%3A58IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Building%20Robust%20Spoken%20Language%20Understanding%20by%20Cross%20Attention%20between%20Phoneme%20Sequence%20and%20ASR%20Hypothesis&rft.jtitle=arXiv.org&rft.au=Wang,%20Zexun&rft.date=2022-03-22&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2642602929%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2642602929&rft_id=info:pmid/&rfr_iscdi=true |