Integrating Speech Recognition and Machine Translation
This paper presents a set of experiments that we conducted in order to optimize the performance of an Arabic/English machine translation system on broadcast news and conversational speech data. Proper integration of speech-to-text (STT) and machine translation (MT) requires special attention to issu...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | IV-1284 |
|---|---|
| container_issue | |
| container_start_page | IV-1281 |
| container_title | |
| container_volume | 4 |
| creator | Matsoukas, S. Bulyko, I. Bing Xiang Kham Nguyen Schwartz, R. Makhoul, J. |
| description | This paper presents a set of experiments that we conducted in order to optimize the performance of an Arabic/English machine translation system on broadcast news and conversational speech data. Proper integration of speech-to-text (STT) and machine translation (MT) requires special attention to issues such as sentence boundary detection, punctuation, STT accuracy, tokenization, conversion of spoken numbers and dates to written form, optimization of MT decoding weights, and scoring. We discuss these issues, and show that a carefully tuned STT/MT integration can lead to significant translation accuracy improvements compared to simply feeding the regular STT output to a text MT system. |
| doi_str_mv | 10.1109/ICASSP.2007.367311 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_4218342</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>4218342</ieee_id><sourcerecordid>4218342</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-e42aab8b5f9f0ec22ccf5cab8ab85966d92bac933bd107a98dffb0e3667708be3</originalsourceid><addsrcrecordid>eNpVjttKw0AURccbGGt_QF_yA4nnzEzm8ijFS6GimAq-lZnJSTpSpyXJi39vRF-EDRvWgs1m7AqhRAR7s1zc1vVLyQF0KZQWiEdsbrVByaUEzY06ZhkX2hZo4f3kn9P2lGVYcSgUSnvOLobhAwCMliZjaplG6no3xtTl9YEobPNXCvsuxTHuU-5Skz-5sI2J8nXv0rBzP_ySnbVuN9D8r2fs7f5uvXgsVs8P09dVEVFXY0GSO-eNr1rbAgXOQ2irMJEplVWqsdy7YIXwDYJ21jRt64GEUlqD8SRm7Pp3NxLR5tDHT9d_bSRHIyQX34lrTEg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Integrating Speech Recognition and Machine Translation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Matsoukas, S. ; Bulyko, I. ; Bing Xiang ; Kham Nguyen ; Schwartz, R. ; Makhoul, J.</creator><creatorcontrib>Matsoukas, S. ; Bulyko, I. ; Bing Xiang ; Kham Nguyen ; Schwartz, R. ; Makhoul, J.</creatorcontrib><description>This paper presents a set of experiments that we conducted in order to optimize the performance of an Arabic/English machine translation system on broadcast news and conversational speech data. Proper integration of speech-to-text (STT) and machine translation (MT) requires special attention to issues such as sentence boundary detection, punctuation, STT accuracy, tokenization, conversion of spoken numbers and dates to written form, optimization of MT decoding weights, and scoring. We discuss these issues, and show that a carefully tuned STT/MT integration can lead to significant translation accuracy improvements compared to simply feeding the regular STT output to a text MT system.</description><identifier>ISSN: 1520-6149</identifier><identifier>ISBN: 9781424407279</identifier><identifier>ISBN: 1424407273</identifier><identifier>EISSN: 2379-190X</identifier><identifier>EISBN: 9781424407286</identifier><identifier>EISBN: 1424407281</identifier><identifier>DOI: 10.1109/ICASSP.2007.367311</identifier><language>eng</language><publisher>IEEE</publisher><subject>Broadcast technology ; Broadcasting ; Contracts ; Decoding ; Educational institutions ; Information science ; Lattices ; Loudspeakers ; Machine Translation ; Pipelines ; Sentence Boundary Detection ; Speech recognition</subject><ispartof>2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, 2007, Vol.4, p.IV-1281-IV-1284</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/4218342$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/4218342$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Matsoukas, S.</creatorcontrib><creatorcontrib>Bulyko, I.</creatorcontrib><creatorcontrib>Bing Xiang</creatorcontrib><creatorcontrib>Kham Nguyen</creatorcontrib><creatorcontrib>Schwartz, R.</creatorcontrib><creatorcontrib>Makhoul, J.</creatorcontrib><title>Integrating Speech Recognition and Machine Translation</title><title>2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07</title><addtitle>ICASSP</addtitle><description>This paper presents a set of experiments that we conducted in order to optimize the performance of an Arabic/English machine translation system on broadcast news and conversational speech data. Proper integration of speech-to-text (STT) and machine translation (MT) requires special attention to issues such as sentence boundary detection, punctuation, STT accuracy, tokenization, conversion of spoken numbers and dates to written form, optimization of MT decoding weights, and scoring. We discuss these issues, and show that a carefully tuned STT/MT integration can lead to significant translation accuracy improvements compared to simply feeding the regular STT output to a text MT system.</description><subject>Broadcast technology</subject><subject>Broadcasting</subject><subject>Contracts</subject><subject>Decoding</subject><subject>Educational institutions</subject><subject>Information science</subject><subject>Lattices</subject><subject>Loudspeakers</subject><subject>Machine Translation</subject><subject>Pipelines</subject><subject>Sentence Boundary Detection</subject><subject>Speech recognition</subject><issn>1520-6149</issn><issn>2379-190X</issn><isbn>9781424407279</isbn><isbn>1424407273</isbn><isbn>9781424407286</isbn><isbn>1424407281</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2007</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVjttKw0AURccbGGt_QF_yA4nnzEzm8ijFS6GimAq-lZnJSTpSpyXJi39vRF-EDRvWgs1m7AqhRAR7s1zc1vVLyQF0KZQWiEdsbrVByaUEzY06ZhkX2hZo4f3kn9P2lGVYcSgUSnvOLobhAwCMliZjaplG6no3xtTl9YEobPNXCvsuxTHuU-5Skz-5sI2J8nXv0rBzP_ySnbVuN9D8r2fs7f5uvXgsVs8P09dVEVFXY0GSO-eNr1rbAgXOQ2irMJEplVWqsdy7YIXwDYJ21jRt64GEUlqD8SRm7Pp3NxLR5tDHT9d_bSRHIyQX34lrTEg</recordid><startdate>200704</startdate><enddate>200704</enddate><creator>Matsoukas, S.</creator><creator>Bulyko, I.</creator><creator>Bing Xiang</creator><creator>Kham Nguyen</creator><creator>Schwartz, R.</creator><creator>Makhoul, J.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>200704</creationdate><title>Integrating Speech Recognition and Machine Translation</title><author>Matsoukas, S. ; Bulyko, I. ; Bing Xiang ; Kham Nguyen ; Schwartz, R. ; Makhoul, J.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-e42aab8b5f9f0ec22ccf5cab8ab85966d92bac933bd107a98dffb0e3667708be3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2007</creationdate><topic>Broadcast technology</topic><topic>Broadcasting</topic><topic>Contracts</topic><topic>Decoding</topic><topic>Educational institutions</topic><topic>Information science</topic><topic>Lattices</topic><topic>Loudspeakers</topic><topic>Machine Translation</topic><topic>Pipelines</topic><topic>Sentence Boundary Detection</topic><topic>Speech recognition</topic><toplevel>online_resources</toplevel><creatorcontrib>Matsoukas, S.</creatorcontrib><creatorcontrib>Bulyko, I.</creatorcontrib><creatorcontrib>Bing Xiang</creatorcontrib><creatorcontrib>Kham Nguyen</creatorcontrib><creatorcontrib>Schwartz, R.</creatorcontrib><creatorcontrib>Makhoul, J.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Matsoukas, S.</au><au>Bulyko, I.</au><au>Bing Xiang</au><au>Kham Nguyen</au><au>Schwartz, R.</au><au>Makhoul, J.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Integrating Speech Recognition and Machine Translation</atitle><btitle>2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07</btitle><stitle>ICASSP</stitle><date>2007-04</date><risdate>2007</risdate><volume>4</volume><spage>IV-1281</spage><epage>IV-1284</epage><pages>IV-1281-IV-1284</pages><issn>1520-6149</issn><eissn>2379-190X</eissn><isbn>9781424407279</isbn><isbn>1424407273</isbn><eisbn>9781424407286</eisbn><eisbn>1424407281</eisbn><abstract>This paper presents a set of experiments that we conducted in order to optimize the performance of an Arabic/English machine translation system on broadcast news and conversational speech data. Proper integration of speech-to-text (STT) and machine translation (MT) requires special attention to issues such as sentence boundary detection, punctuation, STT accuracy, tokenization, conversion of spoken numbers and dates to written form, optimization of MT decoding weights, and scoring. We discuss these issues, and show that a carefully tuned STT/MT integration can lead to significant translation accuracy improvements compared to simply feeding the regular STT output to a text MT system.</abstract><pub>IEEE</pub><doi>10.1109/ICASSP.2007.367311</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1520-6149 |
| ispartof | 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, 2007, Vol.4, p.IV-1281-IV-1284 |
| issn | 1520-6149 2379-190X |
| language | eng |
| recordid | cdi_ieee_primary_4218342 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Broadcast technology Broadcasting Contracts Decoding Educational institutions Information science Lattices Loudspeakers Machine Translation Pipelines Sentence Boundary Detection Speech recognition |
| title | Integrating Speech Recognition and Machine Translation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T00%3A56%3A13IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Integrating%20Speech%20Recognition%20and%20Machine%20Translation&rft.btitle=2007%20IEEE%20International%20Conference%20on%20Acoustics,%20Speech%20and%20Signal%20Processing%20-%20ICASSP%20'07&rft.au=Matsoukas,%20S.&rft.date=2007-04&rft.volume=4&rft.spage=IV-1281&rft.epage=IV-1284&rft.pages=IV-1281-IV-1284&rft.issn=1520-6149&rft.eissn=2379-190X&rft.isbn=9781424407279&rft.isbn_list=1424407273&rft_id=info:doi/10.1109/ICASSP.2007.367311&rft_dat=%3Cieee_6IE%3E4218342%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424407286&rft.eisbn_list=1424407281&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=4218342&rfr_iscdi=true |