{"id":"https://openalex.org/W185597827","doi":"https://doi.org/10.21437/interspeech.2008-209","title":"Multi-stream spectro-temporal features for robust speech recognition","display_name":"Multi-stream spectro-temporal features for robust speech recognition","publication_year":2008,"publication_date":"2008-09-22","ids":{"openalex":"https://openalex.org/W185597827","doi":"https://doi.org/10.21437/interspeech.2008-209","mag":"185597827"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2008-209","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","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":"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":2,"corresponding_author_ids":["https://openalex.org/A5081024424"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":9.3662,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97585191,"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":"898","last_page":"901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.7942065596580505},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7304440140724182},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6291622519493103},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5240623950958252},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5148553252220154},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4138956069946289},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4109462797641754},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4004903733730316},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06528115272521973}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7942065596580505},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7304440140724182},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6291622519493103},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5240623950958252},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5148553252220154},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4138956069946289},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4109462797641754},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4004903733730316},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06528115272521973},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2008-209","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2008-209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2008","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.324.767","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.324.767","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/intrspch08_szhao_nmorgan_final.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.474.9158","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.474.9158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://parlab.eecs.berkeley.edu/sites/all/parlab/files/Multi-stream spectro-temporal features for robust speech recognition.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.75,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W130921173","https://openalex.org/W1484387534","https://openalex.org/W1627087495","https://openalex.org/W1922557984","https://openalex.org/W1971332722","https://openalex.org/W2054883573","https://openalex.org/W2071489795","https://openalex.org/W2106939211","https://openalex.org/W2130426352","https://openalex.org/W2137075158","https://openalex.org/W2151484683","https://openalex.org/W2165712214","https://openalex.org/W2167763959"],"related_works":["https://openalex.org/W2309273277","https://openalex.org/W1769849273","https://openalex.org/W2061937230","https://openalex.org/W1574295218","https://openalex.org/W2547793174","https://openalex.org/W2070212102","https://openalex.org/W2132658536","https://openalex.org/W2544241817","https://openalex.org/W2158882055","https://openalex.org/W2914603036"],"abstract_inverted_index":{"A":[0],"multi-stream":[1,61,83],"approach":[2,84],"to":[3,90],"utilizing":[4],"the":[5,23,29,42,82],"inherently":[6],"large":[7],"number":[8],"of":[9,21,39],"spectro-temporal":[10,43,62,94,101],"features":[11,30,63,95],"for":[12,52,96],"speech":[13,53,97,103],"recognition":[14,54,104],"is":[15],"investigated":[16],"in":[17,41,48,71],"this":[18,26],"study.":[19],"Instead":[20],"reducing":[22],"feature-space":[24],"dimension,":[25],"method":[27],"divides":[28],"into":[31],"streams":[32],"so":[33],"that":[34,81],"each":[35],"represents":[36],"a":[37,66],"patch":[38],"information":[40],"response":[44],"field.":[45],"When":[46],"used":[47],"combination":[49],"with":[50],"MFCCs":[51,76],"under":[55],"both":[56],"clean":[57],"and":[58,92],"noisy":[59],"conditions,":[60],"provide":[64],"roughly":[65],"30":[67],"%":[68],"relative":[69],"improvement":[70],"word-error":[72],"rate":[73],"over":[74],"using":[75],"alone.":[77],"The":[78],"result":[79],"suggests":[80],"may":[85],"be":[86],"an":[87],"effective":[88],"way":[89],"handle":[91],"utilize":[93],"applications.":[98],"Index":[99],"Terms:":[100],"features,":[102]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}