{"id":"https://openalex.org/W4416798567","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249061","title":"From Evaluation to Optimization: Neural Speech Assessment for Downstream Applications","display_name":"From Evaluation to Optimization: Neural Speech Assessment for Downstream Applications","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798567","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249061"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation,Academia Sinica,Taipei,Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation,Academia Sinica,Taipei,Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5044008055"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.47792998,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2582","last_page":"2586"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.8496000170707703,"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":0.8496000170707703,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.07259999960660934,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.040699999779462814,"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/downstream","display_name":"Downstream (manufacturing)","score":0.6409000158309937},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5443000197410583},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.4546999931335449},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.44780001044273376},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4302999973297119},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.40290001034736633},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.3675999939441681},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.36000001430511475}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7120000123977661},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5443000197410583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5324000120162964},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.4546999931335449},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.44780001044273376},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4302999973297119},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.3675999939441681},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C99209842","wikidata":"https://www.wikidata.org/wiki/Q643696","display_name":"Speech perception","level":3,"score":0.34049999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.33239999413490295},{"id":"https://openalex.org/C167310288","wikidata":"https://www.wikidata.org/wiki/Q7564808","display_name":"Sound quality","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C108699837","wikidata":"https://www.wikidata.org/wiki/Q7120750","display_name":"PSQM","level":4,"score":0.3093999922275543},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.30790001153945923},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.30250000953674316},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.28850001096725464},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.28439998626708984},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2777000069618225},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2754000127315521},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.27129998803138733}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249061","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2029098196","https://openalex.org/W2141998673","https://openalex.org/W2963403924","https://openalex.org/W2972394484","https://openalex.org/W2973032625","https://openalex.org/W3096831136","https://openalex.org/W3161480375","https://openalex.org/W3161558238","https://openalex.org/W3197912330","https://openalex.org/W3198003228","https://openalex.org/W3198130028","https://openalex.org/W3202278141","https://openalex.org/W3207551191","https://openalex.org/W3207932315","https://openalex.org/W3212906118","https://openalex.org/W4205483086","https://openalex.org/W4221143458","https://openalex.org/W4225956675","https://openalex.org/W4296068974","https://openalex.org/W4297570641","https://openalex.org/W4297841766","https://openalex.org/W4311167834","https://openalex.org/W4312959668","https://openalex.org/W4319862437","https://openalex.org/W4319997228","https://openalex.org/W4361989120","https://openalex.org/W4372260534","https://openalex.org/W4375869450","https://openalex.org/W4386902723","https://openalex.org/W4387870250","https://openalex.org/W4388107429","https://openalex.org/W4391021560","https://openalex.org/W4391021629","https://openalex.org/W4393859250","https://openalex.org/W4400579243","https://openalex.org/W4402111636","https://openalex.org/W4402112079","https://openalex.org/W4406461266","https://openalex.org/W4407758345","https://openalex.org/W4408352776","https://openalex.org/W4408353481","https://openalex.org/W4410314146","https://openalex.org/W4412944803","https://openalex.org/W4415432920","https://openalex.org/W7076053571"],"related_works":[],"abstract_inverted_index":{"The":[0],"evaluation":[1],"of":[2,12,48,143,154,181],"synthetic":[3],"and":[4,15,30,37,98,146,149,162,171],"processed":[5],"speech":[6,16,50,89,115,144,156,182,185],"has":[7],"long":[8],"been":[9,93],"a":[10,61,71],"cornerstone":[11],"audio":[13],"engineering":[14],"science.":[17],"Although":[18],"subjective":[19],"listening":[20],"tests":[21],"remain":[22],"the":[23,44,141,152,179],"gold":[24],"standard":[25],"for":[26],"assessing":[27],"perceptual":[28,132],"quality":[29,97],"intelligibility,":[31,99],"their":[32,104,122],"high":[33],"cost,":[34],"time":[35],"requirements,":[36],"limited":[38],"scalability":[39],"present":[40],"significant":[41],"challenges":[42],"in":[43,80,106,124],"rapid":[45],"development":[46],"cycles":[47],"modern":[49],"technologies.":[51],"Traditional":[52],"objective":[53],"metrics,":[54],"while":[55],"computationally":[56],"efficient,":[57],"often":[58,78],"rely":[59],"on":[60,121],"clean":[62,75],"reference":[63],"signal,":[64],"making":[65],"them":[66],"intrusive":[67],"approaches.":[68],"This":[69,118],"presents":[70],"major":[72],"limitation,":[73],"as":[74,130],"signals":[76],"are":[77,110],"unavailable":[79],"real-world":[81],"applications.":[82],"In":[83],"recent":[84],"years,":[85],"numerous":[86],"neural":[87],"network-based":[88],"assessment":[90,183],"models":[91,109],"have":[92],"developed":[94],"to":[95,158,176],"predict":[96],"achieving":[100],"promising":[101],"results.":[102],"Beyond":[103],"role":[105,123],"evaluation,":[107],"these":[108],"increasingly":[111],"integrated":[112],"into":[113,184],"downstream":[114,164],"processing":[116,186],"tasks.":[117],"review":[119],"focuses":[120],"two":[125],"main":[126],"areas:":[127],"(1)":[128],"serving":[129],"differentiable":[131],"proxies":[133],"that":[134],"not":[135],"only":[136],"assess":[137],"but":[138],"also":[139],"guide":[140],"optimization":[142],"enhancement":[145],"synthesis":[147],"models;":[148],"(2)":[150],"enabling":[151],"detection":[153],"salient":[155],"characteristics":[157],"support":[159],"more":[160],"precise":[161],"efficient":[163],"processing.":[165],"Finally,":[166],"we":[167],"discuss":[168],"current":[169],"limitations":[170],"outline":[172],"future":[173],"research":[174],"directions":[175],"further":[177],"advance":[178],"integration":[180],"pipelines.":[187]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}