{"id":"https://openalex.org/W2995653082","doi":"https://doi.org/10.1109/tencon.2019.8929240","title":"Scattering transform inspired filterbank learning from raw speech for better acoustic modeling","display_name":"Scattering transform inspired filterbank learning from raw speech for better acoustic modeling","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2995653082","doi":"https://doi.org/10.1109/tencon.2019.8929240","mag":"2995653082"},"language":"en","primary_location":{"id":"doi:10.1109/tencon.2019.8929240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://mpra.ub.uni-muenchen.de/64440/1/MPRA_paper_64440.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5085635571","display_name":"A. Madhavaraj","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"A Madhavaraj","raw_affiliation_strings":["Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069802599","display_name":"A. G. Ramakrishnan","orcid":"https://orcid.org/0000-0002-3646-1955"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"A G Ramakrishnan","raw_affiliation_strings":["Electrical Engineering, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085635571"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.2886,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.68346796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1154","last_page":"1158"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9927999973297119,"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/filter-bank","display_name":"Filter bank","score":0.7855241298675537},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.702023983001709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.672633707523346},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6380469799041748},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5900875926017761},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5393561720848083},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.43507134914398193},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.43506288528442383},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4329524040222168},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.43270236253738403},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.4308139383792877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35757213830947876},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.322644978761673},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23578408360481262},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09014967083930969}],"concepts":[{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.7855241298675537},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.702023983001709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.672633707523346},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6380469799041748},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5900875926017761},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5393561720848083},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.43507134914398193},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.43506288528442383},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4329524040222168},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.43270236253738403},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.4308139383792877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35757213830947876},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.322644978761673},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23578408360481262},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09014967083930969},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tencon.2019.8929240","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tencon.2019.8929240","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"TENCON 2019 - 2019 IEEE Region 10 Conference (TENCON)","raw_type":"proceedings-article"},{"id":"pmh:oai::64440","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/64440/1/MPRA_paper_64440.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"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 Paper"}],"best_oa_location":{"id":"pmh:oai::64440","is_oa":true,"landing_page_url":null,"pdf_url":"https://mpra.ub.uni-muenchen.de/64440/1/MPRA_paper_64440.pdf","source":{"id":"https://openalex.org/S4306401429","display_name":"ePrints@IISc (Indian Institute of Science)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I59270414","host_organization_name":"Indian Institute of Science Bangalore","host_organization_lineage":["https://openalex.org/I59270414"],"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 Paper"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2995653082.pdf"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W285519105","https://openalex.org/W1524333225","https://openalex.org/W1533861849","https://openalex.org/W1541452272","https://openalex.org/W1994906459","https://openalex.org/W2093231248","https://openalex.org/W2154833897","https://openalex.org/W2398826216","https://openalex.org/W2658929981","https://openalex.org/W2889275521","https://openalex.org/W2889427787","https://openalex.org/W2897396694","https://openalex.org/W2917472217","https://openalex.org/W2962901777","https://openalex.org/W2963071736","https://openalex.org/W6631362777","https://openalex.org/W6631943919","https://openalex.org/W6712560600"],"related_works":["https://openalex.org/W3204184292","https://openalex.org/W3176564347","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W3031039437","https://openalex.org/W183202219","https://openalex.org/W2046316885","https://openalex.org/W2015136281","https://openalex.org/W2002689817","https://openalex.org/W2022349254"],"abstract_inverted_index":{"We":[0,178],"propose":[1],"a":[2,18,37,64],"neural":[3,66,84,165],"network":[4,67,127,166],"architecture,":[5],"which":[6,35,73],"operates":[7],"on":[8,137,169],"the":[9,14,32,44,48,70,80,83,92,108,120,126,145,164,182,194],"raw":[10],"speech":[11,49,142],"signal,":[12],"where":[13,91],"first":[15],"layer":[16,28],"contains":[17],"series":[19],"of":[20,26,39,53,82,125,140,157,184],"1D":[21,93],"time-domain":[22],"filters.":[23],"The":[24,51],"output":[25],"this":[27],"is":[29,36],"fed":[30,62],"to":[31,63,68,115,163],"second":[33],"layer,":[34],"bank":[38],"2D-convolution":[40],"filters":[41,96,102],"that":[42],"capture":[43],"spectro-temporal":[45],"modulations":[46],"in":[47,152],"signal.":[50],"outputs":[52],"these":[54],"two":[55],"layers":[56],"are":[57,74,97,111,135],"concatenated,":[58],"normalized":[59],"and":[60,94,103,107,144,159,173,190,192],"then":[61],"feed-forward":[65],"predict":[69],"senone":[71],"posteriors,":[72],"used":[75],"for":[76,187],"ASR":[77,133],"decoding.":[78],"During":[79],"training":[81,191],"network,":[85],"we":[86],"have":[87,179],"employed":[88],"different":[89],"strategies,":[90],"2D":[95],"initialized":[98],"with":[99,119,161],"(a)":[100,113],"Gabor":[101],"(b)":[104,129],"random":[105],"values":[106],"filter":[109,188],"coefficients":[110,172],"either":[112],"allowed":[114],"be":[116],"updated":[117],"along":[118],"other":[121],"affine":[122],"transform":[123],"parameters":[124],"or":[128],"fixed":[130],"during":[131],"training.":[132],"experiments":[134],"conducted":[136],"160":[138],"hours":[139],"Tamil":[141],"data":[143],"proposed":[146],"architecture":[147],"gives":[148],"an":[149],"absolute":[150],"improvement":[151],"word":[153],"error":[154],"rate":[155],"(WER)":[156],"1.35%":[158],"1.21%":[160],"respect":[162],"models":[167],"trained":[168],"mel-frequency":[170],"cepstral":[171],"log-filterbank":[174],"energy":[175],"features,":[176],"respectively.":[177],"also":[180],"compared":[181],"performances":[183],"various":[185],"strategies":[186],"initialization":[189],"reported":[193],"WERs.":[195]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}