{"id":"https://openalex.org/W7148604045","doi":"https://doi.org/10.1109/asru65441.2025.11434770","title":"Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction","display_name":"Bottleneck Transformer-Based Approach for Improved Automatic STOI Score Prediction","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148604045","doi":"https://doi.org/10.1109/asru65441.2025.11434770"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5132826098","display_name":"Amartyaveer","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Amartyaveer","raw_affiliation_strings":["Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132765519","display_name":"Murali Kadambi","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Murali Kadambi","raw_affiliation_strings":["Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019110629","display_name":"C. Sharma","orcid":"https://orcid.org/0000-0002-1312-0429"},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Chandra Mohan Sharma","raw_affiliation_strings":["DRDO,Center for Artificial Intelligence and Robotics (CAIR),India"],"affiliations":[{"raw_affiliation_string":"DRDO,Center for Artificial Intelligence and Robotics (CAIR),India","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101251253","display_name":"Anupam Mandal","orcid":null},"institutions":[{"id":"https://openalex.org/I4210121405","display_name":"Centre for Artificial Intelligence and Robotics","ror":"https://ror.org/01xnbq218","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1340206300","https://openalex.org/I4210121405","https://openalex.org/I4210150591"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anupam Mandal","raw_affiliation_strings":["DRDO,Center for Artificial Intelligence and Robotics (CAIR),India"],"affiliations":[{"raw_affiliation_string":"DRDO,Center for Artificial Intelligence and Robotics (CAIR),India","institution_ids":["https://openalex.org/I4210121405"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046000500","display_name":"Prasanta Ghosh","orcid":"https://orcid.org/0000-0002-2925-1802"},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prasanta Kumar Ghosh","raw_affiliation_strings":["Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Science,SPIRE Lab,Dept of Electrical Engg,Bangalore,India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5132826098"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.67103958,"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":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.0478999987244606,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10363","display_name":"Low-power high-performance VLSI design","score":0.0478999987244606,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T10220","display_name":"Machine Fault Diagnosis Techniques","score":0.023499999195337296,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.021800000220537186,"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/bottleneck","display_name":"Bottleneck","score":0.45669999718666077},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.26570001244544983},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.260699987411499},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.2533999979496002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.525600016117096},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.45669999718666077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3643999993801117},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30649998784065247},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.29420000314712524},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.28949999809265137},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.260699987411499},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.24289999902248383}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434770","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434770","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.7027472853660583}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1552314771","https://openalex.org/W1574170747","https://openalex.org/W2067295501","https://openalex.org/W2092644348","https://openalex.org/W2146710114","https://openalex.org/W2410879554","https://openalex.org/W2963403924","https://openalex.org/W2972394484","https://openalex.org/W3012168345","https://openalex.org/W3043119899","https://openalex.org/W3161558238","https://openalex.org/W3172509117","https://openalex.org/W3202278141","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4296068997","https://openalex.org/W4297841451","https://openalex.org/W4297841568","https://openalex.org/W4311167834","https://openalex.org/W4391021363","https://openalex.org/W4392903985","https://openalex.org/W4393970693","https://openalex.org/W4402111976","https://openalex.org/W4406859936","https://openalex.org/W4407128505","https://openalex.org/W4408353910"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1],"study,":[2],"we":[3],"have":[4,51,57],"presented":[5],"a":[6,18,82],"novel":[7],"approach":[8],"to":[9,87,96,134],"predict":[10],"the":[11,37,70,89,94,102,135],"Short-Time":[12],"Objective":[13],"Intelligibility":[14],"(STOI)":[15],"metric":[16],"using":[17,138],"bottleneck":[19,73],"transformer":[20,95],"architecture.":[21],"Traditional":[22],"methods":[23],"for":[24,65,77,127],"calculating":[25],"STOI":[26,125],"typically":[27],"require":[28],"clean":[29],"reference":[30],"speech.":[31],"This":[32],"limits":[33],"their":[34],"applicability":[35],"in":[36,108,124],"real":[38],"world.":[39],"To":[40],"address":[41],"this,":[42],"numerous":[43],"deep":[44],"learning-based":[45],"non-intrusive":[46],"speech":[47],"quality":[48],"assessment":[49],"models":[50],"garnered":[52],"significant":[53],"interest.":[54],"Many":[55],"studies":[56],"achieved":[58],"commendable":[59],"performance,":[60],"but":[61],"there":[62],"is":[63],"room":[64],"further":[66],"improvement.":[67],"We":[68],"propose":[69],"use":[71],"of":[72,101,110],"transformer,":[74],"convolution":[75],"blocks":[76],"learning":[78,140],"frame-level":[79],"features,":[80],"and":[81,119,130,142],"multi-head":[83],"self-attention":[84],"(MHSA)":[85],"layer":[86],"aggregate":[88],"information.":[90],"These":[91],"components":[92],"enable":[93],"focus":[97],"on":[98],"key":[99],"aspects":[100],"input":[103],"data.":[104],"The":[105],"proposed":[106],"model,":[107],"spite":[109],"having":[111],"relatively":[112],"fewer":[113],"parameters,":[114],"has":[115],"shown":[116],"higher":[117],"correlation":[118],"lower":[120],"mean":[121],"squared":[122],"error":[123],"prediction":[126],"both":[128],"seen":[129],"unseen":[131],"scenarios":[132],"compared":[133],"state-of-the-art":[136],"model":[137],"self-supervised":[139],"(SSL)":[141],"spectral":[143],"features":[144],"as":[145],"input.":[146]},"counts_by_year":[],"updated_date":"2026-04-03T16:44:17.987007","created_date":"2026-04-03T00:00:00"}