{"id":"https://openalex.org/W2403023380","doi":"https://doi.org/10.21437/icslp.1998-305","title":"Performance improvements through combining phone- and syllable-scale information in automatic speech recognition","display_name":"Performance improvements through combining phone- and syllable-scale information in automatic speech recognition","publication_year":1998,"publication_date":"1998-11-30","ids":{"openalex":"https://openalex.org/W2403023380","doi":"https://doi.org/10.21437/icslp.1998-305","mag":"2403023380"},"language":"en","primary_location":{"id":"doi:10.21437/icslp.1998-305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5080017989","display_name":"Su-Lin Wu","orcid":"https://orcid.org/0009-0009-0425-1177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su-Lin Wu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian E. D. Kingsbury","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112003894","display_name":"Nelson Morgan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nelson Morgan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5110588131","display_name":"Steven Greenberg","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":"Steven Greenberg","raw_affiliation_strings":["University of California\u2013Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California\u2013Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 0854","last_page":"0"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998999834060669,"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":0.9973000288009644,"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/speech-recognition","display_name":"Speech recognition","score":0.7906267642974854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7821352481842041},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.7075324058532715},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6583975553512573},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5103282332420349},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4279452860355377},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4003857374191284},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08478894829750061}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7906267642974854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821352481842041},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.7075324058532715},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6583975553512573},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5103282332420349},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4279452860355377},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4003857374191284},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08478894829750061},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/icslp.1998-305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/icslp.1998-305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"5th International Conference on Spoken Language Processing (ICSLP 1998)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.36.2258","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.36.2258","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.icsi.berkeley.edu/pub/speech/papers/icslp98-sylcomb.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W204308143","https://openalex.org/W1498305818","https://openalex.org/W1502283197","https://openalex.org/W1992272902","https://openalex.org/W2016813991","https://openalex.org/W2104981903","https://openalex.org/W2107794610","https://openalex.org/W2129901640","https://openalex.org/W2132658536","https://openalex.org/W2135031448","https://openalex.org/W2137075158","https://openalex.org/W2137644731","https://openalex.org/W2158286329"],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2061937230","https://openalex.org/W2514064218","https://openalex.org/W2978969170","https://openalex.org/W2132658536","https://openalex.org/W2069086264","https://openalex.org/W2911335828","https://openalex.org/W2901371367","https://openalex.org/W2610894233","https://openalex.org/W1502207921"],"abstract_inverted_index":{"Combining":[0],"knowledge":[1],"derived":[2,28],"from":[3,29],"both":[4,114],"syllable-":[5],"(100-250":[6],"ms)":[7,11],"and":[8,58,76,117],"phone-length":[9],"(40-100":[10],"intervals":[12],"in":[13,95],"the":[14,50,54,68,72,74,77,84,88,109,128],"automatic":[15],"speech":[16,103],"recognition":[17,69],"process":[18,70],"can":[19],"yield":[20],"performance":[21],"superior":[22],"to":[23],"that":[24,44],"obtained":[25],"using":[26],"information":[27],"a":[30,92,98,123],"single":[31],"time":[32],"scale":[33],"alone.":[34],"The":[35,105],"results":[36],"are":[37,61],"particularly":[38],"pronounced":[39],"for":[40],"reverberant":[41,119],"test":[42],"conditions":[43],"have":[45],"not":[46],"been":[47],"incorporated":[48],"into":[49],"training":[51],"set.":[52],"In":[53],"present":[55],"study,":[56],"phone-":[57],"syllable-based":[59],"systems":[60],"combined":[62],"at":[63],"three":[64],"distinct":[65],"levels":[66],"of":[67,87],"---":[71],"frame,":[73],"syllable":[75],"entire":[78],"utterance.":[79],"Each":[80],"strategy":[81],"successfully":[82],"integrates":[83],"complementary":[85],"strengths":[86],"individual":[89],"systems,":[90],"yielding":[91,122],"significant":[93],"improvement":[94,126],"accuracy":[96],"on":[97],"small-vocabulary,":[99],"naturally":[100],"spoken,":[101],"telephone":[102],"corpus.":[104],"syllable-level":[106],"combination":[107],"outperformed":[108],"other":[110],"two":[111],"methods":[112],"under":[113],"relatively":[115],"pristine":[116],"moderately":[118],"acoustic":[120],"conditions,":[121],"20-40%":[124],"relative":[125],"over":[127],"baseline.":[129],"1.":[130],"SYLLABLES":[131],"IN":[132],"ASR":[133],"Most":[134],"current":[135],"auto...":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}