{"id":"https://openalex.org/W4385822374","doi":"https://doi.org/10.21437/interspeech.2023-1617","title":"What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions","display_name":"What is Learnt by the LEArnable Front-end (LEAF)? Adapting Per-Channel Energy Normalisation (PCEN) to Noisy Conditions","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385822374","doi":"https://doi.org/10.21437/interspeech.2023-1617"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1617","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.06702","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102879573","display_name":"Hanyu Meng","orcid":"https://orcid.org/0009-0004-6123-0587"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Hanyu Meng","raw_affiliation_strings":["University of New South Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vidhyasaharan Sethu","raw_affiliation_strings":["University of New South Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Eliathamby Ambikairajah","raw_affiliation_strings":["University of New South Wales, Australia"],"affiliations":[{"raw_affiliation_string":"University of New South Wales, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102879573"],"corresponding_institution_ids":["https://openalex.org/I31746571"],"apc_list":null,"apc_paid":null,"fwci":0.2001,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.43342004,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"2898","last_page":"2902"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T11309","display_name":"Music 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/computer-science","display_name":"Computer science","score":0.7675326466560364},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6170198917388916},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6146621704101562},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5921765565872192},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5658822059631348},{"id":"https://openalex.org/keywords/front-and-back-ends","display_name":"Front and back ends","score":0.5592881441116333},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.5059422850608826},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5034100413322449},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4847995340824127},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.46782559156417847},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43056419491767883},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42365431785583496},{"id":"https://openalex.org/keywords/keyword-spotting","display_name":"Keyword spotting","score":0.4126947224140167},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.41015076637268066},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1560972034931183},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11860206723213196},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.11375048756599426},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09669890999794006}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675326466560364},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6170198917388916},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6146621704101562},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5921765565872192},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5658822059631348},{"id":"https://openalex.org/C53016008","wikidata":"https://www.wikidata.org/wiki/Q620167","display_name":"Front and back ends","level":2,"score":0.5592881441116333},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5059422850608826},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5034100413322449},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4847995340824127},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.46782559156417847},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43056419491767883},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42365431785583496},{"id":"https://openalex.org/C2781213101","wikidata":"https://www.wikidata.org/wiki/Q6398558","display_name":"Keyword spotting","level":2,"score":0.4126947224140167},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.41015076637268066},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1560972034931183},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11860206723213196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.11375048756599426},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09669890999794006},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2023-1617","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/interspeech.2023-1617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.06702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.06702","pdf_url":"https://arxiv.org/pdf/2404.06702","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.06702","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.06702","pdf_url":"https://arxiv.org/pdf/2404.06702","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.44999998807907104}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320965","display_name":"University of New South Wales","ror":"https://ror.org/03r8z3t63"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385822374.pdf","grobid_xml":"https://content.openalex.org/works/W4385822374.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2030931454","https://openalex.org/W2102113734","https://openalex.org/W2102372511","https://openalex.org/W2219249508","https://openalex.org/W2317919972","https://openalex.org/W2797583228","https://openalex.org/W2890964092","https://openalex.org/W2899201823","https://openalex.org/W2913314773","https://openalex.org/W2944200841","https://openalex.org/W2952218014","https://openalex.org/W2955425717","https://openalex.org/W2962901777","https://openalex.org/W2963701934","https://openalex.org/W2963881567","https://openalex.org/W2964052309","https://openalex.org/W2982514584","https://openalex.org/W3007948068","https://openalex.org/W3095311338","https://openalex.org/W3161792602","https://openalex.org/W3162501355","https://openalex.org/W3212656946","https://openalex.org/W4220861625","https://openalex.org/W4224916926","https://openalex.org/W4283026521","https://openalex.org/W4287372095","https://openalex.org/W4294437664","https://openalex.org/W4294723414","https://openalex.org/W4297841247","https://openalex.org/W4297841748","https://openalex.org/W4300167667","https://openalex.org/W4312470705","https://openalex.org/W4312856903"],"related_works":["https://openalex.org/W2114097550","https://openalex.org/W4385352507","https://openalex.org/W2918559346","https://openalex.org/W84309476","https://openalex.org/W4286904253","https://openalex.org/W2386245264","https://openalex.org/W4389912005","https://openalex.org/W4391021514","https://openalex.org/W2388033618","https://openalex.org/W2378448517"],"abstract_inverted_index":{"There":[0],"is":[1,21,28,88,93],"increasing":[2],"interest":[3],"in":[4,12,130,154],"the":[5,8,32,37,41,63,69,83,89,99,104,126,150],"use":[6],"of":[7,15,24,26,35,40,101,111],"LEArnable":[9],"Front-end":[10],"(LEAF)":[11],"a":[13,22,108,133],"variety":[14],"speech":[16,138],"processing":[17],"systems.":[18],"However,":[19],"there":[20],"dearth":[23],"analyses":[25],"what":[27],"actually":[29],"learnt":[30],"and":[31,56,60,68,82],"relative":[33],"importance":[34],"training":[36],"different":[38],"components":[39],"front-end.":[42],"In":[43],"this":[44,48,155],"paper,":[45],"we":[46,97],"investigate":[47],"question":[49],"on":[50,136,143],"keyword":[51],"spotting,":[52],"speech-based":[53],"emotion":[54],"recognition":[55],"language":[57],"identification":[58],"tasks":[59],"find":[61],"that":[62,92,123],"filters":[64],"for":[65],"spectral":[66,76],"decomposition":[67],"low":[70],"pass":[71],"filter":[72],"used":[73],"to":[74,114,117,139],"estimate":[75],"energy":[77,85],"variations":[78],"exhibit":[79],"no":[80],"learning":[81],"per-channel":[84],"normalisation":[86],"(PCEN)":[87],"key":[90],"component":[91],"learnt.":[94],"Following":[95],"this,":[96],"explore":[98],"potential":[100],"adapting":[102],"only":[103],"PCEN":[105],"layer":[106],"with":[107],"small":[109],"amount":[110],"noisy":[112,144],"data":[113,146],"enable":[115],"it":[116],"learn":[118],"appropriate":[119],"dynamic":[120],"range":[121],"compression":[122],"better":[124],"suits":[125],"noise":[127],"conditions.":[128],"This":[129],"turn":[131],"enables":[132],"system":[134],"trained":[135],"clean":[137],"work":[140],"more":[141],"accurately":[142],"test":[145],"as":[147],"demonstrated":[148],"by":[149],"experimental":[151],"results":[152],"reported":[153],"paper.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2023-08-15T00:00:00"}