{"id":"https://openalex.org/W96431220","doi":"https://doi.org/10.21437/interspeech.2009-747","title":"Multi-stream to many-stream: using spectro-temporal features for ASR","display_name":"Multi-stream to many-stream: using spectro-temporal features for ASR","publication_year":2009,"publication_date":"2009-09-06","ids":{"openalex":"https://openalex.org/W96431220","doi":"https://doi.org/10.21437/interspeech.2009-747","mag":"96431220"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2009-747","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081024424","display_name":"Sherry Y. Zhao","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sherry Y. Zhao","raw_affiliation_strings":["International Computer Science Institute, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, United States","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026262869","display_name":"Suman Ravuri","orcid":"https://orcid.org/0000-0002-7481-7633"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suman Ravuri","raw_affiliation_strings":["University of California, Berkeley, Berkeley, United States"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley, Berkeley, United States","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":["University of California, Berkeley"],"affiliations":[{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5081024424"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":6.4223,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.9683666,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"2951","last_page":"2954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7961934208869934},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.786811113357544},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6719094514846802},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6555496454238892},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6549768447875977},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5830913782119751},{"id":"https://openalex.org/keywords/streams","display_name":"STREAMS","score":0.4951764643192291},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4007965624332428},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38326817750930786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7961934208869934},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.786811113357544},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6719094514846802},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6555496454238892},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6549768447875977},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5830913782119751},{"id":"https://openalex.org/C42090638","wikidata":"https://www.wikidata.org/wiki/Q4048907","display_name":"STREAMS","level":2,"score":0.4951764643192291},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4007965624332428},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38326817750930786},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2009-747","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2009-747","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2009","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.519.6381","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.519.6381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.icsi.berkeley.edu/pubs/speech/is2009_sz1_sr1_nm1.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W103244930","https://openalex.org/W185597827","https://openalex.org/W1627087495","https://openalex.org/W1922557984","https://openalex.org/W1971332722","https://openalex.org/W2054883573","https://openalex.org/W2071489795","https://openalex.org/W2101596234","https://openalex.org/W2103621378","https://openalex.org/W2118858754","https://openalex.org/W2130426352","https://openalex.org/W2151484683","https://openalex.org/W2161224286","https://openalex.org/W2165712214"],"related_works":["https://openalex.org/W2010317732","https://openalex.org/W2483328176","https://openalex.org/W2383111961","https://openalex.org/W2061705145","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W193205649","https://openalex.org/W2372385138"],"abstract_inverted_index":{"We":[0],"report":[1],"progress":[2],"in":[3,32,61,68,78,94],"the":[4,41,59,75,92,95,106],"use":[5],"of":[6,43,108,126],"multi-stream":[7],"spectro-temporal":[8,48,109,134],"features":[9,110,127],"for":[10,26,128],"both":[11],"small":[12,36],"and":[13,29,65],"large":[14,96,124],"vocabulary":[15,37,97],"automatic":[16,129],"speech":[17,38,130,136],"recognition":[18,39,100,137],"tasks.":[19],"Features":[20],"are":[21],"divided":[22],"into":[23,111],"multiple":[24,112],"streams":[25,50,113],"parallel":[27],"processing":[28],"dynamic":[30],"utilization":[31],"this":[33],"approach.":[34],"For":[35],"experiments,":[40],"in-corporation":[42],"up":[44],"to":[45,119],"28":[46],"dynamically-weighted":[47],"feature":[49],"along":[51],"with":[52],"MFCCs":[53],"yields":[54,86],"roughly":[55],"21%":[56],"improvement":[57,67,73,90],"on":[58,74],"baseline":[60,76,93],"low":[62,98],"noise":[63,99],"conditions":[64],"47%":[66],"noise-added":[69],"conditions,":[70],"a":[71,87],"greater":[72],"than":[77],"our":[79],"previous":[80],"work.":[81],"A":[82],"four":[83],"stream":[84],"framework":[85],"14":[88],"%":[89],"over":[91],"experiment.":[101],"These":[102],"results":[103],"suggest":[104],"that":[105],"division":[107],"may":[114],"be":[115],"an":[116,122],"effective":[117],"way":[118],"flexibly":[120],"utilize":[121],"inherently":[123],"number":[125],"recognition.":[131],"Index":[132],"Terms:":[133],"features,":[135],"1.":[138]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}