{"id":{"repo_id":"lethbridge","oai_identifier":"oai:opus.uleth.ca:10133/5815"},"canonical_url":"https://search.dev.ndltd.org/etd/lethbridge/oai:opus.uleth.ca:10133/5815","repository":{"repo_id":"lethbridge","name":"University of Lethbridge","base_url":"https://opus.uleth.ca/server/oai/request"},"display":{"title":"Biologically-inspired auditory artificial intelligence for speech recognition in multi-talker environments","abstract":"Understanding speech in the presence of distracting talkers is a difficult computational problem known as the cocktail party problem. Motivated by auditory processing in the human brain, this thesis developed a neural network to isolate the speech of a single talker given binaural input containing a target talker and multiple distractors. In this research the network is called a Binaural Speaker Isolation FFTNet or BSINet for short. To compare the performance of BSINet to human participant performance on recognizing the target talker's speech with a varying number of distractors, a \"cocktail party\" dataset was designed and made available online. This dataset also enables the comparison of network performance to human participant performance. Using the Word-Error-Rate metric for evaluation, this research finds that BSINet performs comparably to the human participants. Thus BSINet provides significant advancement for solving the challenging cocktail party problem.","abstract_html":"Understanding speech in the presence of distracting talkers is a difficult computational problem known as the cocktail party problem. Motivated by auditory processing in the human brain, this thesis developed a neural network to isolate the speech of a single talker given binaural input containing a target talker and multiple distractors. In this research the network is called a Binaural Speaker Isolation FFTNet or BSINet for short. To compare the performance of BSINet to human participant performance on recognizing the target talker's speech with a varying number of distractors, a "cocktail party" dataset was designed and made available online. This dataset also enables the comparison of network performance to human participant performance. Using the Word-Error-Rate metric for evaluation, this research finds that BSINet performs comparably to the human participants. Thus BSINet provides significant advancement for solving the challenging cocktail party problem.","abstract_has_math":false,"creators":["Grasse, Lukas Walter Neufeld"],"institution":null,"degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020","date_published":"2020","updated_at":"2026-07-27T20:02:05Z","subjects":["Speech Recognition","Denoising","Speaker Isolation","Cocktail Party Problem","Auditory selective attention","Neural networks (Computer science)","Speech perception","Automatic speech recognition","Directional hearing","Auditory perception","Dissertations, Academic"],"languages":[],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:10133/5815"],"render_values":[{"text":"hdl:10133/5815","href":null,"code":true}]}]},"links":{"outbound_url":null,"outbound_label":null,"outbound_source":null},"metadata_groups":[{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.issued","label":"Date","values":["2020"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Speech Recognition","Denoising","Speaker Isolation","Cocktail Party Problem","Auditory selective attention","Neural networks (Computer science)","Speech perception","Automatic speech recognition","Directional hearing","Auditory perception","Dissertations, Academic"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["hdl:10133/5815"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.other","label":"Dc Description Other","values":["Understanding speech in the presence of distracting talkers is a difficult computational problem known as the cocktail party problem. Motivated by auditory processing in the human brain, this thesis developed a neural network to isolate the speech of a single talker given binaural input containing a target talker and multiple distractors. In this research the network is called a Binaural Speaker Isolation FFTNet or BSINet for short. To compare the performance of BSINet to human participant performance on recognizing the target talker's speech with a varying number of distractors, a \"cocktail party\" dataset was designed and made available online. This dataset also enables the comparison of network performance to human participant performance. Using the Word-Error-Rate metric for evaluation, this research finds that BSINet performs comparably to the human participants. Thus BSINet provides significant advancement for solving the challenging cocktail party problem."]},{"key":"dc:title","label":"Title","values":["Biologically-inspired auditory artificial intelligence for speech recognition in multi-talker environments"]}]}],"canonical_facts":{"dc:date.issued":["2020"],"dc:description.other":["Understanding speech in the presence of distracting talkers is a difficult computational problem known as the cocktail party problem. Motivated by auditory processing in the human brain, this thesis developed a neural network to isolate the speech of a single talker given binaural input containing a target talker and multiple distractors. In this research the network is called a Binaural Speaker Isolation FFTNet or BSINet for short. To compare the performance of BSINet to human participant performance on recognizing the target talker's speech with a varying number of distractors, a \"cocktail party\" dataset was designed and made available online. This dataset also enables the comparison of network performance to human participant performance. Using the Word-Error-Rate metric for evaluation, this research finds that BSINet performs comparably to the human participants. Thus BSINet provides significant advancement for solving the challenging cocktail party problem."],"dc:identifier":["hdl:10133/5815"],"dc:subject":["Speech Recognition","Denoising","Speaker Isolation","Cocktail Party Problem","Auditory selective attention","Neural networks (Computer science)","Speech perception","Automatic speech recognition","Directional hearing","Auditory perception","Dissertations, Academic"],"dc:title":["Biologically-inspired auditory artificial intelligence for speech recognition in multi-talker environments"],"dc:type":["Thesis"]},"updated_at":"2026-07-27T20:02:05Z"}