{"id":"https://openalex.org/W2813631418","doi":"https://doi.org/10.21437/interspeech.2018-2293","title":"Tone Recognition Using Lifters and CTC","display_name":"Tone Recognition Using Lifters and CTC","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2813631418","doi":"https://doi.org/10.21437/interspeech.2018-2293","mag":"2813631418"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2293","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1807.02465","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040757409","display_name":"Loren Lugosch","orcid":"https://orcid.org/0000-0002-5024-8667"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Loren Lugosch","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083452139","display_name":"Vikrant Singh Tomar","orcid":"https://orcid.org/0009-0005-6509-9499"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vikrant Singh Tomar","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040757409"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06857815,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9991000294685364,"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":0.9976999759674072,"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":0.7660787105560303},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7506240010261536},{"id":"https://openalex.org/keywords/tone","display_name":"Tone (literature)","score":0.7349342107772827},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.7147312760353088},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6082500219345093},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5955265760421753},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5861968994140625},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5231384038925171},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4936131238937378},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4658907651901245},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.4499278962612152},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.44931405782699585},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37178704142570496},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2546282410621643}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7660787105560303},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7506240010261536},{"id":"https://openalex.org/C2780583480","wikidata":"https://www.wikidata.org/wiki/Q1366327","display_name":"Tone (literature)","level":2,"score":0.7349342107772827},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.7147312760353088},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6082500219345093},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5955265760421753},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5861968994140625},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5231384038925171},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4936131238937378},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4658907651901245},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.4499278962612152},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.44931405782699585},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37178704142570496},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2546282410621643},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","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/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"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":4,"locations":[{"id":"doi:10.21437/interspeech.2018-2293","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2293","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1807.02465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.02465","pdf_url":"https://arxiv.org/pdf/1807.02465","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:2813631418","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1807.02465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1807.02465","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1807.02465","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1807.02465","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1807.02465","pdf_url":"https://arxiv.org/pdf/1807.02465","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6299999952316284}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2813631418.pdf","grobid_xml":"https://content.openalex.org/works/W2813631418.grobid-xml"},"referenced_works_count":14,"referenced_works":["https://openalex.org/W103244930","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1648698152","https://openalex.org/W1992153276","https://openalex.org/W2085628288","https://openalex.org/W2087395764","https://openalex.org/W2127141656","https://openalex.org/W2509088535","https://openalex.org/W2749455670","https://openalex.org/W2755682845","https://openalex.org/W2773798130","https://openalex.org/W2964121744","https://openalex.org/W3019584399"],"related_works":["https://openalex.org/W2963437406","https://openalex.org/W2945616452","https://openalex.org/W2015535859","https://openalex.org/W103244930","https://openalex.org/W2074339272","https://openalex.org/W2355170890","https://openalex.org/W2080541440","https://openalex.org/W2158890602","https://openalex.org/W3002785901","https://openalex.org/W2160899562","https://openalex.org/W2234788913","https://openalex.org/W3090571339","https://openalex.org/W2075550158","https://openalex.org/W1505251852","https://openalex.org/W3154592304","https://openalex.org/W2009810445","https://openalex.org/W3021306136","https://openalex.org/W2625027024","https://openalex.org/W2778926431","https://openalex.org/W1537449681"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,26,29,35,47,62],"new":[6],"method":[7,18,58],"for":[8,14],"recognizing":[9],"tones":[10,45],"in":[11,78,81],"continuous":[12],"speech":[13,23,67],"tonal":[15],"languages.":[16],"The":[17,53],"works":[19],"by":[20],"converting":[21],"the":[22,41,56,75,79],"signal":[24],"to":[25,73],"cepstrogram,":[27],"extracting":[28],"sequence":[30,43],"of":[31,44,55,83],"cepstral":[32],"features":[33],"using":[34,46],"convolutional":[36],"neural":[37],"network,":[38],"and":[39,70],"predicting":[40],"underlying":[42],"connectionist":[48],"temporal":[49],"classification":[50],"(CTC)":[51],"network.":[52],"performance":[54],"proposed":[57],"is":[59,71],"evaluated":[60],"on":[61],"freely":[63],"available":[64],"Mandarin":[65],"Chinese":[66],"corpus,":[68],"AISHELL-1,":[69],"shown":[72],"outperform":[74],"existing":[76],"techniques":[77],"literature":[80],"terms":[82],"tone":[84],"error":[85],"rate":[86],"(TER).":[87]},"counts_by_year":[],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}