{"id":"https://openalex.org/W3163596720","doi":"https://doi.org/10.1109/icassp39728.2021.9414776","title":"Probing Acoustic Representations for Phonetic Properties","display_name":"Probing Acoustic Representations for Phonetic Properties","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163596720","doi":"https://doi.org/10.1109/icassp39728.2021.9414776","mag":"3163596720"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5038995529","display_name":"Danni Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I79576946","display_name":"University of Pennsylvania","ror":"https://ror.org/00b30xv10","country_code":"US","type":"education","lineage":["https://openalex.org/I79576946"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Danni Ma","raw_affiliation_strings":["University of Pennsylvania,Department of Computer and Information Science"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Department of Computer and Information Science","institution_ids":["https://openalex.org/I79576946"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088320958","display_name":"Neville Ryant","orcid":"https://orcid.org/0000-0003-2545-6912"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neville Ryant","raw_affiliation_strings":["University of Pennsylvania,Linguistic Data Consortium","Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Linguistic Data Consortium","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055868875","display_name":"Mark Liberman","orcid":"https://orcid.org/0000-0002-8605-9024"},"institutions":[{"id":"https://openalex.org/I4210120198","display_name":"Pennsylvania Academic Library Consortium","ror":"https://ror.org/02m6s1q30","country_code":"US","type":"archive","lineage":["https://openalex.org/I4210120198"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Liberman","raw_affiliation_strings":["University of Pennsylvania,Linguistic Data Consortium","Linguistic Data Consortium, University of Pennsylvania"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pennsylvania,Linguistic Data Consortium","institution_ids":["https://openalex.org/I4210120198"]},{"raw_affiliation_string":"Linguistic Data Consortium, University of Pennsylvania","institution_ids":["https://openalex.org/I4210120198"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.9181,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94526251,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"311","last_page":"315"},"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/T11309","display_name":"Music 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/T10181","display_name":"Natural Language Processing Techniques","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8249448537826538},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7135119438171387},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6608021855354309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5180090069770813},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5012049674987793},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47478339076042175},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.452900767326355},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.44052380323410034},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4214555621147156},{"id":"https://openalex.org/keywords/transferability","display_name":"Transferability","score":0.4147951602935791},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.41396570205688477},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.3763493299484253},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2630766034126282},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15676885843276978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08161148428916931}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8249448537826538},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7135119438171387},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6608021855354309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5180090069770813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5012049674987793},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47478339076042175},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.452900767326355},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.44052380323410034},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4214555621147156},{"id":"https://openalex.org/C61272859","wikidata":"https://www.wikidata.org/wiki/Q7834031","display_name":"Transferability","level":3,"score":0.4147951602935791},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.41396570205688477},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.3763493299484253},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2630766034126282},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15676885843276978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08161148428916931},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414776","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414776","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.699999988079071,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2077804127","https://openalex.org/W2101234009","https://openalex.org/W2190506272","https://openalex.org/W2191779130","https://openalex.org/W2250539671","https://openalex.org/W2296681920","https://openalex.org/W2896457183","https://openalex.org/W2933138175","https://openalex.org/W2951216052","https://openalex.org/W2962739339","https://openalex.org/W2963571336","https://openalex.org/W2964204621","https://openalex.org/W2964303116","https://openalex.org/W2973049979","https://openalex.org/W2973157397","https://openalex.org/W2979476256","https://openalex.org/W2982223350","https://openalex.org/W3015265920","https://openalex.org/W3015412285","https://openalex.org/W3020336359","https://openalex.org/W3024182269","https://openalex.org/W3025035610","https://openalex.org/W3036601975","https://openalex.org/W3096485810","https://openalex.org/W3112034174","https://openalex.org/W3121914243","https://openalex.org/W3148040514","https://openalex.org/W3196595845","https://openalex.org/W4294170691","https://openalex.org/W4297808394","https://openalex.org/W6629717138","https://openalex.org/W6675354045","https://openalex.org/W6682691769","https://openalex.org/W6687152286","https://openalex.org/W6731763572","https://openalex.org/W6755207826","https://openalex.org/W6769196770","https://openalex.org/W6769686700","https://openalex.org/W6777232839","https://openalex.org/W6780218876","https://openalex.org/W6786127183","https://openalex.org/W6786669483","https://openalex.org/W6788328058","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2340308015","https://openalex.org/W2121652828","https://openalex.org/W4288040805","https://openalex.org/W2125329182"],"abstract_inverted_index":{"Pre-trained":[0],"acoustic":[1,125],"representations":[2,35,83],"such":[3],"as":[4],"wav2vec":[5],"and":[6,37,52,75,91],"DeCoAR":[7],"have":[8],"attained":[9],"impressive":[10],"word":[11],"error":[12],"rates":[13],"(WER)":[14],"for":[15],"speech":[16],"recognition":[17],"benchmarks,":[18],"particularly":[19],"when":[20],"labeled":[21],"data":[22,97],"is":[23,27],"limited.":[24],"But":[25],"little":[26],"known":[28],"about":[29],"what":[30],"phonetic":[31,60],"properties":[32],"these":[33],"various":[34,123],"acquire,":[36],"how":[38],"well":[39],"they":[40],"encode":[41],"transferable":[42],"features":[43,48,67,78],"of":[44,71,87,114,122],"speech.":[45],"We":[46],"compare":[47],"from":[49,68,79],"two":[50],"conventional":[51],"four":[53],"pre-trained":[54,93],"systems":[55],"in":[56],"some":[57,85],"simple":[58],"frame-level":[59],"classification":[61],"tasks,":[62],"with":[63,106],"classifiers":[64],"trained":[65],"on":[66,77,94],"one":[69],"version":[70],"the":[72,104,107],"TIMIT":[73],"dataset":[74],"tested":[76],"another.":[80],"All":[81],"contextualized":[82],"offered":[84],"level":[86],"transferability":[88],"across":[89],"domains,":[90],"models":[92],"more":[95],"audio":[96],"give":[98],"better":[99],"results;":[100],"but":[101],"overall,":[102],"DeCoAR,":[103],"system":[105],"simplest":[108],"architecture,":[109],"performs":[110],"best.":[111],"This":[112],"type":[113],"benchmarking":[115],"analysis":[116],"can":[117],"thus":[118],"uncover":[119],"relative":[120],"strengths":[121],"proposed":[124],"representations.":[126]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":5}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}