{"id":"https://openalex.org/W152325841","doi":"https://doi.org/10.21437/interspeech.2006-232","title":"A wavelet-based parameterization for speech/music segmentation","display_name":"A wavelet-based parameterization for speech/music segmentation","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W152325841","doi":"https://doi.org/10.21437/interspeech.2006-232","mag":"152325841"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-232","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","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/A5010540888","display_name":"Emmanuel Didiot","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"E. Didiot","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073463405","display_name":"Irina Illina","orcid":"https://orcid.org/0000-0003-2598-4643"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"I. Illina","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087867823","display_name":"Orlando Mella","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"O. Mella","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046546502","display_name":"Dominique Fohr","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D. Fohr","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111482011","display_name":"Jean\u2010Paul Haton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jean-Paul Haton","raw_affiliation_strings":["Analysis, perception and recognition of speech"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Analysis, perception and recognition of speech","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2934,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.77835239,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"paper 1361","last_page":"Mon3CaP.5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9896000027656555,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9887999892234802,"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":0.787787914276123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7519367933273315},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6422598361968994},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6318443417549133},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49692729115486145},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.494019091129303},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.46935588121414185},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45388704538345337},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4520355463027954},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4147588014602661},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.4115549325942993},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3709993064403534},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3201272487640381},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12874963879585266}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.787787914276123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7519367933273315},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6422598361968994},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6318443417549133},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49692729115486145},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.494019091129303},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.46935588121414185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45388704538345337},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4520355463027954},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4147588014602661},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.4115549325942993},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3709993064403534},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3201272487640381},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12874963879585266},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2006-232","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-232","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-00103569v1","is_oa":false,"landing_page_url":"https://hal.science/hal-00103569","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2006, pp.653","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2349769824","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2144773493","https://openalex.org/W1494724239","https://openalex.org/W2059040236"],"abstract_inverted_index":{"The":[0],"problem":[1,9],"of":[2,34,46,103,107],"speech/music":[3,115],"discrimination":[4,26,116],"is":[5],"a":[6,32,43,99],"challenging":[7],"research":[8],"which":[10,41],"significantly":[11],"impacts":[12],"Automatic":[13],"Speech":[14],"Recognition":[15],"(ASR)":[16],"performance.":[17],"This":[18],"paper":[19],"proposes":[20],"new":[21],"features":[22],"for":[23,74,77,113],"the":[24,35,80,84,92,104,110,114],"Speech/Music":[25],"task.":[27,117],"We":[28,54],"propose":[29],"to":[30],"use":[31],"decomposition":[33],"audio":[36],"signal":[37,49],"based":[38],"on":[39,109],"wavelets,":[40],"allows":[42],"good":[44],"analysis":[45],"non":[47],"stationary":[48],"like":[50],"speech":[51],"or":[52],"music.":[53],"compute":[55],"different":[56,81],"energy":[57],"types":[58],"in":[59],"each":[60],"frequency":[61],"band":[62],"obtained":[63],"from":[64],"wavelet":[65,86],"decomposition.":[66],"Two":[67],"class/non-class":[68],"classifiers":[69],"are":[70],"used":[71],":":[72],"one":[73,76],"speech/non-speech,":[75],"music/non-music.":[78],"On":[79],"test":[82],"corpora,":[83],"proposed":[85],"approach":[87],"gives":[88],"better":[89],"results":[90],"than":[91],"MFCC":[93],"one.":[94],"For":[95],"instance,":[96],"we":[97],"have":[98],"significant":[100],"relative":[101],"improvements":[102],"error":[105],"rate":[106],"71.6%":[108],"``Scheirer''":[111],"corpus":[112]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}