{"id":"https://openalex.org/W2972794572","doi":"https://doi.org/10.21437/interspeech.2019-2981","title":"Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings","display_name":"Unsupervised Acoustic Segmentation and Clustering Using Siamese Network Embeddings","publication_year":2019,"publication_date":"2019-09-13","ids":{"openalex":"https://openalex.org/W2972794572","doi":"https://doi.org/10.21437/interspeech.2019-2981","mag":"2972794572"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2019-2981","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","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/A5045247662","display_name":"Saurabhchand Bhati","orcid":"https://orcid.org/0000-0001-6477-3895"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saurabhchand Bhati","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001110193","display_name":"Shekhar Nayak","orcid":"https://orcid.org/0000-0002-4277-4851"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shekhar Nayak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067617924","display_name":"K. Sri Rama Murty","orcid":"https://orcid.org/0000-0002-6355-5287"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K. Sri Rama Murty","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5050632169","display_name":"Najim Dehak","orcid":"https://orcid.org/0000-0002-4489-5753"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Najim Dehak","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"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/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998999834060669,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7661231756210327},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.708141565322876},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5931766629219055},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5050368905067444},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.398398220539093}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7661231756210327},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.708141565322876},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5931766629219055},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5050368905067444},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.398398220539093}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2019-2981","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2019-2981","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2019","raw_type":"proceedings-article"},{"id":"pmh:oai:raiith.iith.ac.in:7025","is_oa":false,"landing_page_url":"http://raiith.iith.ac.in/7025/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400292","display_name":"Research Archive of Indian Institute of Technology Hyderabad (Indian Institute of Technology Hyderabad)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I65181880","host_organization_name":"Indian Institute of Technology Hyderabad","host_organization_lineage":["https://openalex.org/I65181880"],"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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W126222424","https://openalex.org/W1545920196","https://openalex.org/W1796128977","https://openalex.org/W2020607164","https://openalex.org/W2052697931","https://openalex.org/W2100768664","https://openalex.org/W2126203737","https://openalex.org/W2160815625","https://openalex.org/W2166637769","https://openalex.org/W2170659185","https://openalex.org/W2190506272","https://openalex.org/W2251025892","https://openalex.org/W2398490608","https://openalex.org/W2404799143","https://openalex.org/W2468716020","https://openalex.org/W2747192917","https://openalex.org/W2963620343","https://openalex.org/W2964169922"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W2350741829","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Unsupervised":[0],"discovery":[1],"of":[2,14,96,179],"acoustic":[3,22,114,154,184],"units":[4],"from":[5,49,55,93,127],"the":[6,11,21,37,50,56,84,97,102,108,119,128,152,164,180],"raw":[7,120],"speech":[8,16,98],"signal":[9,99],"forms":[10],"core":[12],"objective":[13],"zero-resource":[15],"processing.":[17],"It":[18],"involves":[19],"identifying":[20],"segment":[23,41,62],"boundaries":[24,42,140],"and":[25,82,100,116,146,167,186],"consistently":[26],"assigning":[27],"unique":[28,169],"labels":[29],"to":[30,67,75,162,173],"acoustically":[31,174],"similar":[32,175],"segments.":[33,155,176],"In":[34],"this":[35,144],"work,":[36],"possible":[38],"candidates":[39,64],"for":[40,113,134,151,183],"are":[43,65,141,149],"identified":[44],"in":[45],"an":[46],"unsupervised":[47],"manner":[48],"kernel":[51],"Gram":[52,124],"matrix":[53,125],"computed":[54,126],"Mel-frequency":[57],"cepstral":[58],"coefficients":[59],"(MFCC).":[60],"These":[61,105],"boundary":[63,135],"used":[66,161],"train":[68],"a":[69,168],"siamese":[70,88,109,129,147,165],"network,":[71],"that":[72,78],"is":[73,160,171,188],"intended":[74],"learn":[76],"embeddings":[77,89,110,130,148],"minimize":[79],"intrasegment":[80],"distances":[81],"maximize":[83],"intersegment":[85,103],"distances.":[86],"The":[87,123,137,177],"capture":[90],"phonetic":[91],"information":[92],"longer":[94],"contexts":[95],"enhance":[101],"discriminability.":[104],"properties":[106],"make":[107],"better":[111],"suited":[112],"segmentation":[115,185],"clustering":[117,187],"than":[118],"MFCC":[121],"features.":[122],"provides":[131],"unambiguous":[132],"evidence":[133],"locations.":[136],"initial":[138],"candidate":[139],"refined":[142],"using":[143],"evidence,":[145],"extracted":[150],"new":[153],"A":[156],"graph":[157],"growing":[158],"approach":[159],"cluster":[163],"embeddings,":[166],"label":[170],"assigned":[172],"performance":[178],"proposed":[181],"method":[182],"evaluated":[189],"on":[190],"Zero":[191],"Resource":[192],"2017":[193],"database.":[194]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}