{"id":"https://openalex.org/W2529337537","doi":"https://doi.org/10.1109/icassp.2017.7952190","title":"Very deep convolutional neural networks for raw waveforms","display_name":"Very deep convolutional neural networks for raw waveforms","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2529337537","doi":"https://doi.org/10.1109/icassp.2017.7952190","mag":"2529337537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100752241","display_name":"Wei Dai","orcid":"https://orcid.org/0009-0001-7532-4048"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004854444","display_name":"Chia Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chia Dai","raw_affiliation_strings":["Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112694715","display_name":"Shuhui Qu","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuhui Qu","raw_affiliation_strings":["Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100648014","display_name":"Juncheng Li","orcid":"https://orcid.org/0000-0001-7314-6754"},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Juncheng Li","raw_affiliation_strings":["Bosch Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research","institution_ids":["https://openalex.org/I4210151956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110454109","display_name":"Samarjit Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210151956","display_name":"Robert Bosch (India)","ror":"https://ror.org/04my8ty22","country_code":"IN","type":"company","lineage":["https://openalex.org/I4210151956","https://openalex.org/I889804353"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Samarjit Das","raw_affiliation_strings":["Bosch Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bosch Research","institution_ids":["https://openalex.org/I4210151956"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":22.7204,"has_fulltext":false,"cited_by_count":340,"citation_normalized_percentile":{"value":0.99694596,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"421","last_page":"425"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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":0.9998000264167786,"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":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.7717921137809753},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549936771392822},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7513248920440674},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6839369535446167},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6297817230224609},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5665682554244995},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5648585557937622},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5452739000320435},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5330072045326233},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5149298906326294},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.4157698452472687},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.41499006748199463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3704371154308319},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.27442753314971924},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27406686544418335},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.2060195505619049},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.06711190938949585}],"concepts":[{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.7717921137809753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549936771392822},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7513248920440674},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6839369535446167},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6297817230224609},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5665682554244995},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5648585557937622},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5452739000320435},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5330072045326233},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5149298906326294},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.4157698452472687},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.41499006748199463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3704371154308319},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27442753314971924},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27406686544418335},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2060195505619049},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.06711190938949585},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2017.7952190","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952190","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1542280630","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1903029394","https://openalex.org/W1922655562","https://openalex.org/W1972567154","https://openalex.org/W2035424729","https://openalex.org/W2038484192","https://openalex.org/W2095705004","https://openalex.org/W2096733369","https://openalex.org/W2097117768","https://openalex.org/W2145287260","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2198724430","https://openalex.org/W2271840356","https://openalex.org/W2398826216","https://openalex.org/W2401869809","https://openalex.org/W2408093180","https://openalex.org/W3099206234","https://openalex.org/W6631943919","https://openalex.org/W6674330103","https://openalex.org/W6684191040","https://openalex.org/W6712560600","https://openalex.org/W6713197546"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3082178636","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1617617605","https://openalex.org/W2530913366"],"abstract_inverted_index":{"Learning":[0],"acoustic":[1,76],"models":[2,16,185],"directly":[3,46],"from":[4],"the":[5,93,102,121,137,142,146,153,160,182],"raw":[6],"waveform":[7],"data":[8],"with":[9,54,145,155,162,181],"minimal":[10],"processing":[11,75],"is":[12,79,179],"challenging.":[13],"Current":[14],"waveform-based":[15],"have":[17],"generally":[18],"used":[19],"very":[20,39,65,130],"few":[21],"(~2)":[22],"convolutional":[23,41,123],"layers,":[24,59],"which":[25],"might":[26],"be":[27],"insufficient":[28],"for":[29,74,172],"building":[30],"high-level":[31],"discriminative":[32],"features.":[33,188],"In":[34],"this":[35],"work,":[36],"we":[37],"propose":[38],"deep":[40],"neural":[42],"networks":[43,97],"(CNNs)":[44],"that":[45,152],"use":[47,103,115],"time-domain":[48],"waveforms":[49],"as":[50],"inputs.":[51],"Our":[52,96,149],"CNNs,":[53],"up":[55],"to":[56,62,110,125,135],"34":[57],"weight":[58,157,164],"are":[60,98],"efficient":[61],"optimize":[63],"over":[64,167],"long":[66],"sequences":[67],"(e.g.,":[68],"vector":[69],"of":[70,90,104,184],"size":[71],"32000),":[72],"necessary":[73],"waveforms.":[77],"This":[78],"achieved":[80],"through":[81],"batch":[82],"normalization,":[83],"residual":[84],"learning,":[85],"and":[86,108,178],"a":[87,116],"careful":[88],"design":[89],"down-sampling":[91],"in":[92,120,169],"initial":[94],"layers.":[95],"fully":[99,105],"convolutional,":[100],"without":[101],"connected":[106],"layers":[107,158,165],"dropout,":[109],"maximize":[111],"representation":[112],"learning.":[113],"We":[114,140],"large":[117],"receptive":[118,132],"field":[119],"first":[122],"layer":[124],"mimic":[126],"bandpass":[127],"filters,":[128],"but":[129],"small":[131],"fields":[133],"subsequently":[134],"control":[136],"model":[138],"capacity.":[139],"demonstrate":[141],"performance":[143,183],"gains":[144],"deeper":[147],"models.":[148],"evaluation":[150],"shows":[151],"CNN":[154,161],"18":[156],"outperforms":[159],"3":[163],"by":[166],"15%":[168],"absolute":[170],"accuracy":[171],"an":[173],"environmental":[174],"sound":[175],"recognition":[176],"task":[177],"competitive":[180],"using":[186],"log-mel":[187]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":27},{"year":2024,"cited_by_count":33},{"year":2023,"cited_by_count":47},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":50},{"year":2020,"cited_by_count":47},{"year":2019,"cited_by_count":41},{"year":2018,"cited_by_count":36},{"year":2017,"cited_by_count":6}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}