Improving a phoneme classification neural network through problem decomposition
The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors revie...
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 | 826 vol.2 |
|---|---|
| container_issue | |
| container_start_page | 821 |
| container_title | |
| container_volume | ii |
| creator | Pratt, L.Y. Kamm, C.A. |
| description | The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping tasks. It is shown that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations.< > |
| doi_str_mv | 10.1109/IJCNN.1991.155440 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_155440</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>155440</ieee_id><sourcerecordid>155440</sourcerecordid><originalsourceid>FETCH-LOGICAL-i104t-4ee24222f7c33beac8d984fbe9d08503e1d1784fd839dd3e40d543e7214873153</originalsourceid><addsrcrecordid>eNotj81OwzAQhC0hJKD0AeDkF0jYje3GOaKIn6KqvcC5cuJNY0jiyE5BvD2pylw-aTQz0jB2h5AiQvGwfiu32xSLAlNUSkq4YDeQaxCAK4lXbBnjJ8ySClZKX7Pduh-D_3bDgRs-tn6gnnjdmRhd42ozOT_wgY7BdDOmHx---NQGfzy0fO5VHfXcUu370Ud3Ct-yy8Z0kZb_XLCP56f38jXZ7F7W5eMmcQhySiRRJrMsa_JaiIpMrW2hZVNRYUErEIQW89mwWhTWCpJglRSUZyh1LlCJBbs_7zoi2o_B9Sb87s-XxR-WUU3n</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Improving a phoneme classification neural network through problem decomposition</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Pratt, L.Y. ; Kamm, C.A.</creator><creatorcontrib>Pratt, L.Y. ; Kamm, C.A.</creatorcontrib><description>The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping tasks. It is shown that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations.< ></description><identifier>ISBN: 0780301641</identifier><identifier>ISBN: 9780780301641</identifier><identifier>DOI: 10.1109/IJCNN.1991.155440</identifier><language>eng</language><publisher>IEEE</publisher><subject>Arithmetic ; Artificial intelligence ; Computer science ; Data preprocessing ; Neural networks ; Performance evaluation ; Search problems ; Signal mapping ; Speech ; Testing</subject><ispartof>IJCNN-91-Seattle International Joint Conference on Neural Networks, 1991, Vol.ii, p.821-826 vol.2</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/155440$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/155440$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Pratt, L.Y.</creatorcontrib><creatorcontrib>Kamm, C.A.</creatorcontrib><title>Improving a phoneme classification neural network through problem decomposition</title><title>IJCNN-91-Seattle International Joint Conference on Neural Networks</title><addtitle>IJCNN</addtitle><description>The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping tasks. It is shown that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations.< ></description><subject>Arithmetic</subject><subject>Artificial intelligence</subject><subject>Computer science</subject><subject>Data preprocessing</subject><subject>Neural networks</subject><subject>Performance evaluation</subject><subject>Search problems</subject><subject>Signal mapping</subject><subject>Speech</subject><subject>Testing</subject><isbn>0780301641</isbn><isbn>9780780301641</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>1991</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNotj81OwzAQhC0hJKD0AeDkF0jYje3GOaKIn6KqvcC5cuJNY0jiyE5BvD2pylw-aTQz0jB2h5AiQvGwfiu32xSLAlNUSkq4YDeQaxCAK4lXbBnjJ8ySClZKX7Pduh-D_3bDgRs-tn6gnnjdmRhd42ozOT_wgY7BdDOmHx---NQGfzy0fO5VHfXcUu370Ud3Ct-yy8Z0kZb_XLCP56f38jXZ7F7W5eMmcQhySiRRJrMsa_JaiIpMrW2hZVNRYUErEIQW89mwWhTWCpJglRSUZyh1LlCJBbs_7zoi2o_B9Sb87s-XxR-WUU3n</recordid><startdate>1991</startdate><enddate>1991</enddate><creator>Pratt, L.Y.</creator><creator>Kamm, C.A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>1991</creationdate><title>Improving a phoneme classification neural network through problem decomposition</title><author>Pratt, L.Y. ; Kamm, C.A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i104t-4ee24222f7c33beac8d984fbe9d08503e1d1784fd839dd3e40d543e7214873153</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>1991</creationdate><topic>Arithmetic</topic><topic>Artificial intelligence</topic><topic>Computer science</topic><topic>Data preprocessing</topic><topic>Neural networks</topic><topic>Performance evaluation</topic><topic>Search problems</topic><topic>Signal mapping</topic><topic>Speech</topic><topic>Testing</topic><toplevel>online_resources</toplevel><creatorcontrib>Pratt, L.Y.</creatorcontrib><creatorcontrib>Kamm, C.A.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Pratt, L.Y.</au><au>Kamm, C.A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Improving a phoneme classification neural network through problem decomposition</atitle><btitle>IJCNN-91-Seattle International Joint Conference on Neural Networks</btitle><stitle>IJCNN</stitle><date>1991</date><risdate>1991</risdate><volume>ii</volume><spage>821</spage><epage>826 vol.2</epage><pages>821-826 vol.2</pages><isbn>0780301641</isbn><isbn>9780780301641</isbn><abstract>The authors discuss how a methodology called problem decomposition can be applied to an AP-net, a neural network for mapping acoustic spectra to phoneme classes. The network's task is to recognize phonemes from a large corpus of multiple-speaker, continuously spoken sentences. The authors review previous AP-net systems and present results from a decomposition study in which smaller networks trained to recognize subsets of phonemes are combined into a larger network for the full signal-to-phoneme mapping tasks. It is shown that, by using this problem decomposition methodology, comparable performance can be obtained in significantly fewer arithmetic operations.< ></abstract><pub>IEEE</pub><doi>10.1109/IJCNN.1991.155440</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISBN: 0780301641 |
| ispartof | IJCNN-91-Seattle International Joint Conference on Neural Networks, 1991, Vol.ii, p.821-826 vol.2 |
| issn | |
| language | eng |
| recordid | cdi_ieee_primary_155440 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Arithmetic Artificial intelligence Computer science Data preprocessing Neural networks Performance evaluation Search problems Signal mapping Speech Testing |
| title | Improving a phoneme classification neural network through problem decomposition |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T21%3A53%3A51IST&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=Improving%20a%20phoneme%20classification%20neural%20network%20through%20problem%20decomposition&rft.btitle=IJCNN-91-Seattle%20International%20Joint%20Conference%20on%20Neural%20Networks&rft.au=Pratt,%20L.Y.&rft.date=1991&rft.volume=ii&rft.spage=821&rft.epage=826%20vol.2&rft.pages=821-826%20vol.2&rft.isbn=0780301641&rft.isbn_list=9780780301641&rft_id=info:doi/10.1109/IJCNN.1991.155440&rft_dat=%3Cieee_6IE%3E155440%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=155440&rfr_iscdi=true |