{"id":"https://openalex.org/W4416799441","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249016","title":"Single-Channel Speech Enhancement in Spherical-Mapped Short-Time Spectral Domain","display_name":"Single-Channel Speech Enhancement in Spherical-Mapped Short-Time Spectral Domain","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799441","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249016"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249016","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/A5107744486","display_name":"Yu Morinaga","orcid":null},"institutions":[{"id":"https://openalex.org/I125852741","display_name":"Kanazawa Institute of Technology","ror":"https://ror.org/02ws33e43","country_code":"JP","type":"education","lineage":["https://openalex.org/I125852741"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yu Morinaga","raw_affiliation_strings":["Kanazawa Institute of Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa Institute of Technology,Japan","institution_ids":["https://openalex.org/I125852741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107744336","display_name":"Naoto Kotake","orcid":null},"institutions":[{"id":"https://openalex.org/I125852741","display_name":"Kanazawa Institute of Technology","ror":"https://ror.org/02ws33e43","country_code":"JP","type":"education","lineage":["https://openalex.org/I125852741"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Naoto Kotake","raw_affiliation_strings":["Kanazawa Institute of Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa Institute of Technology,Japan","institution_ids":["https://openalex.org/I125852741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112293685","display_name":"Iori Hashimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I125852741","display_name":"Kanazawa Institute of Technology","ror":"https://ror.org/02ws33e43","country_code":"JP","type":"education","lineage":["https://openalex.org/I125852741"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Iori Hashimoto","raw_affiliation_strings":["Kanazawa Institute of Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa Institute of Technology,Japan","institution_ids":["https://openalex.org/I125852741"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074250128","display_name":"Suehiro Shimauchi","orcid":null},"institutions":[{"id":"https://openalex.org/I125852741","display_name":"Kanazawa Institute of Technology","ror":"https://ror.org/02ws33e43","country_code":"JP","type":"education","lineage":["https://openalex.org/I125852741"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Suehiro Shimauchi","raw_affiliation_strings":["Kanazawa Institute of Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa Institute of Technology,Japan","institution_ids":["https://openalex.org/I125852741"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112827702","display_name":"Shigeaki Aoki","orcid":null},"institutions":[{"id":"https://openalex.org/I125852741","display_name":"Kanazawa Institute of Technology","ror":"https://ror.org/02ws33e43","country_code":"JP","type":"education","lineage":["https://openalex.org/I125852741"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeaki Aoki","raw_affiliation_strings":["Kanazawa Institute of Technology,Japan"],"affiliations":[{"raw_affiliation_string":"Kanazawa Institute of Technology,Japan","institution_ids":["https://openalex.org/I125852741"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5107744486"],"corresponding_institution_ids":["https://openalex.org/I125852741"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.48023933,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9932000041007996,"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":0.9932000041007996,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.0019000000320374966,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.0013000000035390258,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7340999841690063},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.4717999994754791},{"id":"https://openalex.org/keywords/spectral-shape-analysis","display_name":"Spectral shape analysis","score":0.45239999890327454},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41100001335144043},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.4065999984741211},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.3961000144481659},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.3817000091075897},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.3783000111579895},{"id":"https://openalex.org/keywords/time-domain","display_name":"Time domain","score":0.3776000142097473}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7340999841690063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5058000087738037},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47099998593330383},{"id":"https://openalex.org/C152822103","wikidata":"https://www.wikidata.org/wiki/Q7575207","display_name":"Spectral shape analysis","level":3,"score":0.45239999890327454},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41100001335144043},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4065999984741211},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4025999903678894},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40139999985694885},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3961000144481659},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.3817000091075897},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.3783000111579895},{"id":"https://openalex.org/C103824480","wikidata":"https://www.wikidata.org/wiki/Q185889","display_name":"Time domain","level":2,"score":0.3776000142097473},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3732999861240387},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.36959999799728394},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36660000681877136},{"id":"https://openalex.org/C2983668108","wikidata":"https://www.wikidata.org/wiki/Q280453","display_name":"Spectral analysis","level":3,"score":0.35920000076293945},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.353300005197525},{"id":"https://openalex.org/C3018181011","wikidata":"https://www.wikidata.org/wiki/Q6849688","display_name":"Contrast enhancement","level":3,"score":0.3280999958515167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C89735579","wikidata":"https://www.wikidata.org/wiki/Q6795894","display_name":"Maximum entropy spectral estimation","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C2985906921","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Spectral properties","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C30049272","wikidata":"https://www.wikidata.org/wiki/Q6555326","display_name":"Spectral density estimation","level":3,"score":0.29249998927116394},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.2874000072479248},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.2851000130176544},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.27720001339912415},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2689000070095062},{"id":"https://openalex.org/C114700698","wikidata":"https://www.wikidata.org/wiki/Q2882278","display_name":"Spectral bands","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249016","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249016","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":17,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1901129140","https://openalex.org/W2044893557","https://openalex.org/W2095072097","https://openalex.org/W2141998673","https://openalex.org/W2165700458","https://openalex.org/W2291877678","https://openalex.org/W2940275453","https://openalex.org/W2964058413","https://openalex.org/W2998161426","https://openalex.org/W3096408984","https://openalex.org/W4289665794","https://openalex.org/W4375869466","https://openalex.org/W4387938956","https://openalex.org/W4390628729","https://openalex.org/W4403126494","https://openalex.org/W4408345619"],"related_works":[],"abstract_inverted_index":{"A":[0],"single-channel":[1],"speech":[2,71],"enhancement":[3,72],"method":[4,68],"is":[5],"proposed,":[6],"which":[7,74],"performs":[8],"feature":[9],"extraction":[10],"and":[11,77,95],"mask":[12],"processing":[13],"in":[14,22,50,80,88],"spherical-mapped":[15],"short-time":[16,36,59,83],"spectral":[17,37,60,84],"(SMSTS)":[18],"domain.":[19],"The":[20,44],"features":[21],"the":[23,53,66,81],"SMSTS":[24],"domain":[25,85],"are":[26],"represented":[27],"as":[28,86],"three-dimensional":[29,41],"direction":[30,45],"cosines,":[31],"obtained":[32],"by":[33],"mapping":[34],"complexvalued":[35],"components":[38,79],"onto":[39],"a":[40],"unit":[42],"sphere.":[43],"cosines":[46],"have":[47],"continuous":[48],"properties,":[49],"contrast":[51],"to":[52],"inherently":[54],"discontinuous":[55],"nature":[56],"of":[57,90],"conventional":[58,70],"phase.":[61],"Simulation":[62],"results":[63],"demonstrate":[64],"that":[65],"proposed":[67],"outperforms":[69],"approaches,":[73],"use":[75],"real":[76],"imaginary":[78],"complex-valued":[82],"features,":[87],"terms":[89],"scale-invariant":[91],"signal-to-distortion":[92],"ratio":[93],"(SI-SDR)":[94],"shorttime":[96],"objective":[97],"intelligibility":[98],"(STOI)":[99],"metrics.":[100]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}