{"id":"https://openalex.org/W2155977751","doi":"https://doi.org/10.1109/icassp.2005.1415150","title":"Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription","display_name":"Acoustic Training from Heterogeneous Data Sources: Experiments in Mandarin Conversational Telephone Speech Transcription","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2155977751","doi":"https://doi.org/10.1109/icassp.2005.1415150","mag":"2155977751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5073006801","display_name":"Stavros Tsakalidis","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"S. Tsakalidis","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070594684","display_name":"Bill Byrne","orcid":"https://orcid.org/0000-0003-1896-4492"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB","US"],"is_corresponding":false,"raw_author_name":"W. Byrne","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","Department of Engineering, University of Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University, Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]},{"raw_affiliation_string":"Department of Engineering, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"461","last_page":"464"},"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":0.9994999766349792,"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":0.9972000122070312,"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/normalization","display_name":"Normalization (sociology)","score":0.8463826775550842},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7765707969665527},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.7368579506874084},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7351840138435364},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7165166139602661},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5900167226791382},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4752216935157776},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4170929491519928},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34671756625175476},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3279433846473694}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.8463826775550842},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7765707969665527},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.7368579506874084},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7351840138435364},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7165166139602661},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5900167226791382},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4752216935157776},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4170929491519928},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34671756625175476},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3279433846473694},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2005.1415150","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415150","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.226.3539","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.226.3539","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://malach.umiacs.umd.edu/pubs/ST_05_Acoust_Trng.pdf","raw_type":"text"},{"id":"pmh:oai:generic.eprints.org:326396","is_oa":false,"landing_page_url":"http://publications.eng.cam.ac.uk/326396/","pdf_url":null,"source":{"id":"https://openalex.org/S4406922847","display_name":"Cambridge University Engineering Department Publications Database","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"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":23,"referenced_works":["https://openalex.org/W163096959","https://openalex.org/W419081377","https://openalex.org/W1576943562","https://openalex.org/W1599512239","https://openalex.org/W1608451537","https://openalex.org/W1631260214","https://openalex.org/W1846073453","https://openalex.org/W2002342963","https://openalex.org/W2049633694","https://openalex.org/W2072073255","https://openalex.org/W2082474452","https://openalex.org/W2113911479","https://openalex.org/W2129937325","https://openalex.org/W2136836257","https://openalex.org/W2155388323","https://openalex.org/W2157590573","https://openalex.org/W2169883442","https://openalex.org/W2308181013","https://openalex.org/W6606720101","https://openalex.org/W6636246093","https://openalex.org/W6636811518","https://openalex.org/W6638728282","https://openalex.org/W6684803408"],"related_works":["https://openalex.org/W2992378684","https://openalex.org/W2964829415","https://openalex.org/W2122233706","https://openalex.org/W642007152","https://openalex.org/W2105439218","https://openalex.org/W2186896963","https://openalex.org/W4372346152","https://openalex.org/W4361192867","https://openalex.org/W3143423642","https://openalex.org/W2131711534"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,80],"investigate":[4,81],"the":[5,41,71,74,82,91],"use":[6],"of":[7,73,84],"heterogeneous":[8],"data":[9,43,65],"sources":[10],"for":[11,20],"acoustic":[12,17,24,29,77],"training.":[13,47],"We":[14],"describe":[15],"an":[16,22],"normalization":[18,93],"procedure":[19],"enlarging":[21],"ASR":[23],"training":[25,34,87],"set":[26,35],"with":[27,90],"out-of-domain":[28,42,64],"data.":[30],"A":[31],"larger":[32],"in-domain":[33],"is":[36],"created":[37],"by":[38],"effectively":[39],"transforming":[40],"before":[44],"incorporation":[45],"in":[46,51,88],"Baseline":[48],"experimental":[49],"results":[50],"Mandarin":[52],"conversational":[53],"telephone":[54],"speech":[55],"transcription":[56],"show":[57],"that":[58],"a":[59],"simple":[60],"attempt":[61],"to":[62],"add":[63],"degrades":[66],"performance.":[67],"Preliminary":[68],"experiments":[69],"assess":[70],"effectiveness":[72],"proposed":[75],"cross-corpus":[76,92],"normalization.":[78],"Furthermore,":[79],"behavior":[83],"speaker":[85],"adaptive":[86],"conjunction":[89],"procedure.":[94]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}