{"id":"https://openalex.org/W4402115974","doi":"https://doi.org/10.21437/interspeech.2024-1234","title":"Personalized Speech Enhancement Without a Separate Speaker Embedding Model","display_name":"Personalized Speech Enhancement Without a Separate Speaker Embedding Model","publication_year":2024,"publication_date":"2024-09-01","ids":{"openalex":"https://openalex.org/W4402115974","doi":"https://doi.org/10.21437/interspeech.2024-1234"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2024-1234","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1234","pdf_url":"https://www.isca-archive.org/interspeech_2024/parnamaa24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2024/parnamaa24_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023048113","display_name":"Tanel P\u00e4rnamaa","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tanel P\u00e4rnamaa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5058867828","display_name":"Ando Saabas","orcid":"https://orcid.org/0009-0001-9449-0404"},"institutions":[{"id":"https://openalex.org/I4210105678","display_name":"Microsoft (Finland)","ror":"https://ror.org/01nehjf29","country_code":"FI","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210105678"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Ando Saabas","raw_affiliation_strings":["Microsoft Corporation"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation","institution_ids":["https://openalex.org/I4210105678"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4863","last_page":"4867"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9987999796867371,"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":0.9987999796867371,"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":0.986299991607666,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9351000189781189,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7584269046783447},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.715591549873352},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5801750421524048},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5785102844238281},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2664329409599304},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.058452457189559937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7584269046783447},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.715591549873352},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5801750421524048},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5785102844238281},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2664329409599304},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.058452457189559937}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2024-1234","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1234","pdf_url":"https://www.isca-archive.org/interspeech_2024/parnamaa24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2024-1234","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2024-1234","pdf_url":"https://www.isca-archive.org/interspeech_2024/parnamaa24_interspeech.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402115974.pdf","grobid_xml":"https://content.openalex.org/works/W4402115974.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2081900870","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853"],"abstract_inverted_index":{"Personalized":[0],"speech":[1],"enhancement":[2],"(PSE)":[3],"models":[4],"can":[5],"improve":[6],"the":[7,16,37,46,54,58,63,68,84,104],"audio":[8],"quality":[9],"of":[10,18,36,57,87],"teleconferencing":[11],"systems":[12],"by":[13,112],"adapting":[14],"to":[15,31,45,52],"characteristics":[17],"a":[19,26,33,71,89],"speaker's":[20],"voice.However,":[21],"most":[22],"existing":[23],"methods":[24],"require":[25],"separate":[27,72],"speaker":[28,38,64,91],"embedding":[29,92],"model":[30,60,93],"extract":[32],"vector":[34],"representation":[35,56],"from":[39],"enrollment":[40],"audio,":[41],"which":[42],"adds":[43],"complexity":[44],"training":[47],"and":[48,97],"deployment":[49],"process.We":[50],"propose":[51],"use":[53],"internal":[55],"PSE":[59],"itself":[61],"as":[62],"embedding,":[65],"thereby":[66],"avoiding":[67],"need":[69],"for":[70],"model.We":[73],"show":[74],"that":[75],"our":[76,101],"approach":[77,102],"performs":[78],"equally":[79],"well":[80],"or":[81],"better":[82],"than":[83],"standard":[85],"method":[86],"using":[88],"pre-trained":[90],"on":[94],"noise":[95],"suppression":[96],"echo":[98],"cancellation":[99],"tasks.Moreover,":[100],"surpasses":[103],"ICASSP":[105],"2023":[106],"Deep":[107],"Noise":[108],"Suppression":[109],"Challenge":[110],"winner":[111],"0.15":[113],"in":[114],"Mean":[115],"Opinion":[116],"Score.":[117]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}