Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion
We present a novel conversational-context aware end-to-end speech recognizer based on a gated neural network that incorporates conversational-context/word/speech embeddings. Unlike conventional speech recognition models, our model learns longer conversational-context information that spans across se...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | |
| container_volume | |
| creator | Kim, Suyoun Dalmia, Siddharth Metze, Florian |
| description | We present a novel conversational-context aware end-to-end speech recognizer
based on a gated neural network that incorporates
conversational-context/word/speech embeddings. Unlike conventional speech
recognition models, our model learns longer conversational-context information
that spans across sentences and is consequently better at recognizing long
conversations. Specifically, we propose to use the text-based external word
and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end
framework, yielding a significant improvement in word error rate with better
conversational-context representation. We evaluated the models on the
Switchboard conversational speech corpus and show that our model outperforms
standard end-to-end speech recognition models. |
| doi_str_mv | 10.48550/arxiv.1906.11604 |
| format | Article |
| fullrecord | <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_1906_11604</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>1906_11604</sourcerecordid><originalsourceid>FETCH-LOGICAL-a674-16bd2d9d4739d122673bf598ca4f0b4df4b4eb66ca355eeaf8ae21aac6d573443</originalsourceid><addsrcrecordid>eNotj71qwzAURrV0KGkfoFP1AnIl68f2GIyTFgKFJru5sq4SQSIF2Q3p29dJOx2-M3xwCHkRvFC11vwN8jVcCtFwUwhhuHok2zVM6Gh3suhciPuRhki76NiU2Ay6PSMOB_qFQ9rHMIUUqU-ZtileMI9wE3Bk85zwOtHV9ziLJ_Lg4Tji8z8XZLfqdu0723yuP9rlhoGpFBPGutI1TlWycaIsTSWt1009gPLcKueVVWiNGUBqjQi-BiwFwGCcrqRSckFe_27vVf05hxPkn_5W19_r5C8gsUsZ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion</title><source>arXiv.org</source><creator>Kim, Suyoun ; Dalmia, Siddharth ; Metze, Florian</creator><creatorcontrib>Kim, Suyoun ; Dalmia, Siddharth ; Metze, Florian</creatorcontrib><description>We present a novel conversational-context aware end-to-end speech recognizer
based on a gated neural network that incorporates
conversational-context/word/speech embeddings. Unlike conventional speech
recognition models, our model learns longer conversational-context information
that spans across sentences and is consequently better at recognizing long
conversations. Specifically, we propose to use the text-based external word
and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end
framework, yielding a significant improvement in word error rate with better
conversational-context representation. We evaluated the models on the
Switchboard conversational speech corpus and show that our model outperforms
standard end-to-end speech recognition models.</description><identifier>DOI: 10.48550/arxiv.1906.11604</identifier><language>eng</language><subject>Computer Science - Computation and Language ; Computer Science - Sound</subject><creationdate>2019-06</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,886</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/1906.11604$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.1906.11604$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Kim, Suyoun</creatorcontrib><creatorcontrib>Dalmia, Siddharth</creatorcontrib><creatorcontrib>Metze, Florian</creatorcontrib><title>Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion</title><description>We present a novel conversational-context aware end-to-end speech recognizer
based on a gated neural network that incorporates
conversational-context/word/speech embeddings. Unlike conventional speech
recognition models, our model learns longer conversational-context information
that spans across sentences and is consequently better at recognizing long
conversations. Specifically, we propose to use the text-based external word
and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end
framework, yielding a significant improvement in word error rate with better
conversational-context representation. We evaluated the models on the
Switchboard conversational speech corpus and show that our model outperforms
standard end-to-end speech recognition models.</description><subject>Computer Science - Computation and Language</subject><subject>Computer Science - Sound</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNotj71qwzAURrV0KGkfoFP1AnIl68f2GIyTFgKFJru5sq4SQSIF2Q3p29dJOx2-M3xwCHkRvFC11vwN8jVcCtFwUwhhuHok2zVM6Gh3suhciPuRhki76NiU2Ay6PSMOB_qFQ9rHMIUUqU-ZtileMI9wE3Bk85zwOtHV9ziLJ_Lg4Tji8z8XZLfqdu0723yuP9rlhoGpFBPGutI1TlWycaIsTSWt1009gPLcKueVVWiNGUBqjQi-BiwFwGCcrqRSckFe_27vVf05hxPkn_5W19_r5C8gsUsZ</recordid><startdate>20190627</startdate><enddate>20190627</enddate><creator>Kim, Suyoun</creator><creator>Dalmia, Siddharth</creator><creator>Metze, Florian</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20190627</creationdate><title>Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion</title><author>Kim, Suyoun ; Dalmia, Siddharth ; Metze, Florian</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a674-16bd2d9d4739d122673bf598ca4f0b4df4b4eb66ca355eeaf8ae21aac6d573443</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computer Science - Computation and Language</topic><topic>Computer Science - Sound</topic><toplevel>online_resources</toplevel><creatorcontrib>Kim, Suyoun</creatorcontrib><creatorcontrib>Dalmia, Siddharth</creatorcontrib><creatorcontrib>Metze, Florian</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Kim, Suyoun</au><au>Dalmia, Siddharth</au><au>Metze, Florian</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion</atitle><date>2019-06-27</date><risdate>2019</risdate><abstract>We present a novel conversational-context aware end-to-end speech recognizer
based on a gated neural network that incorporates
conversational-context/word/speech embeddings. Unlike conventional speech
recognition models, our model learns longer conversational-context information
that spans across sentences and is consequently better at recognizing long
conversations. Specifically, we propose to use the text-based external word
and/or sentence embeddings (i.e., fastText, BERT) within an end-to-end
framework, yielding a significant improvement in word error rate with better
conversational-context representation. We evaluated the models on the
Switchboard conversational speech corpus and show that our model outperforms
standard end-to-end speech recognition models.</abstract><doi>10.48550/arxiv.1906.11604</doi><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | DOI: 10.48550/arxiv.1906.11604 |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_arxiv_primary_1906_11604 |
| source | arXiv.org |
| subjects | Computer Science - Computation and Language Computer Science - Sound |
| title | Gated Embeddings in End-to-End Speech Recognition for Conversational-Context Fusion |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-15T21%3A42%3A01IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Gated%20Embeddings%20in%20End-to-End%20Speech%20Recognition%20for%20Conversational-Context%20Fusion&rft.au=Kim,%20Suyoun&rft.date=2019-06-27&rft_id=info:doi/10.48550/arxiv.1906.11604&rft_dat=%3Carxiv_GOX%3E1906_11604%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true |