{"id":{"repo_id":"gatech","oai_identifier":"oai:repository.gatech.edu:1853/76868"},"canonical_url":"https://search.ndltd.org/etd/gatech/oai:repository.gatech.edu:1853/76868","repository":{"repo_id":"gatech","name":"Georgia Tech","base_url":"https://repository.gatech.edu/server/oai/request"},"display":{"title":"Towards perceptual metrics for audio quality assessment","abstract":"Recent years have seen considerable advances in audio synthesis with deep generative models known as Neural Audio Synthesizers (NAS). However, the state-of-the-art is very difficult to quantify directly; different studies use different evaluation methodologies and metrics when reporting results, making a direct comparison to other systems difficult. Furthermore, in the case of objective metrics, the perceptual relevance and meaning of the reported metrics in most cases is unknown, prohibiting any conclusive insights with respect to the generated audio quality. This dissertation work focuses on: 1. Investigating how effective contemporary metrics are at capturing the audio quality of sounds generated from NAS systems, 2. Assessing the behavior of popularly used embedding distance measures and the embeddings that are used and, 3. Designing metrics that can measure the difference in audio quality between two signals, given that one of them is a reference signal. Thus, the proposed work will focus on developing objective metrics to provide comparable, reproducible and perceptually meaningful audio quality measurement strategies to help set the foundation for future NAS development.","abstract_html":"Recent years have seen considerable advances in audio synthesis with deep generative models known as Neural Audio Synthesizers (NAS). However, the state-of-the-art is very difficult to quantify directly; different studies use different evaluation methodologies and metrics when reporting results, making a direct comparison to other systems difficult. Furthermore, in the case of objective metrics, the perceptual relevance and meaning of the reported metrics in most cases is unknown, prohibiting any conclusive insights with respect to the generated audio quality. This dissertation work focuses on: 1. Investigating how effective contemporary metrics are at capturing the audio quality of sounds generated from NAS systems, 2. Assessing the behavior of popularly used embedding distance measures and the embeddings that are used and, 3. Designing metrics that can measure the difference in audio quality between two signals, given that one of them is a reference signal. Thus, the proposed work will focus on developing objective metrics to provide comparable, reproducible and perceptually meaningful audio quality measurement strategies to help set the foundation for future NAS development.","abstract_has_math":false,"creators":["Vinay, Ashvala"],"institution":"Georgia Institute of Technology","degree_name":null,"degree_level":"Doctoral","degree_discipline":null,"degree_department":"Music","school":null,"contributors":[],"advisors":["Lerch, Alexander"],"committee_chairs":[],"committee_members":["Arthur, Claire","Quinton, Elio","von Coler, Henrik"],"year":2024,"date_issued":"2024-08-28","date_published":"2024-08-28","updated_at":"2026-11-19T03:50:26Z","subjects":["Audio Quality Assessment","Sound Quality","Signal Processing"],"languages":["en_US"],"rights":[],"rights_urls":[],"identifier_entries":[],"person_identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/1853/76868","outbound_label":"Handle","outbound_source":"dc:identifier.uri","record_url":"https://hdl.handle.net/1853/76868","record_label":"Repository record","record_kind":"handle","record_source":"dc:identifier.uri","download_url":null,"download_label":null,"download_source":null,"access_status":null,"embargo_until":null,"access_note":null},"source_record":{"url":"https://repository.gatech.edu/server/oai/request?verb=GetRecord&metadataPrefix=dim&identifier=oai%3Arepository.gatech.edu%3A1853%2F76868","prefix":"dim"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Lerch, Alexander"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Arthur, Claire","Quinton, Elio","von Coler, Henrik"]},{"key":"dc:contributor.department","label":"Department","values":["Music"]},{"key":"dc:contributor.other","label":"Dc Contributor Other","values":["College of Design","School of Music"]},{"key":"dc:creator","label":"Author","values":["Vinay, Ashvala"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-01-15T13:48:21Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-01-15T13:48:21Z"]},{"key":"dc:date.created","label":"Dc Date Created","values":["2024-12"]},{"key":"dc:date.issued","label":"Date","values":["2024-08-28"]},{"key":"dc:date.submitted","label":"Dc Date Submitted","values":["December 2024"]},{"key":"dc:date.updated","label":"Dc Date Updated","values":["2025-01-15T13:48:22Z"]},{"key":"dc:publisher","label":"Institution","values":["Georgia Institute of Technology"]},{"key":"dc:relation.advisorentity","label":"Dc Relation Advisorentity","values":["1809048a-a767-4f23-ae76-c0eebf261485"]},{"key":"dc:relation.ispartofseries","label":"Dc Relation Ispartofseries","values":["Doctor of Philosophy with a Major in Music Technology"]},{"key":"dc:relation.orgunit","label":"Dc Relation Orgunit","values":["c997b6a0-7e87-4a6f-b6fc-932d776ba8d0","92d2daaa-80f2-4d99-b464-ab7c1125fc55"]},{"key":"dc:relation.seriesentity","label":"Dc Relation Seriesentity","values":["d1fd9079-2e93-4803-98c8-8365a28e0761"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Doctoral"]},{"key":"thesis:degree_program","label":"Thesis Degree Program","values":["Music Technology"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Audio Quality Assessment","Sound Quality","Signal Processing"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/1853/76868"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Recent years have seen considerable advances in audio synthesis with deep generative models known as Neural Audio Synthesizers (NAS). However, the state-of-the-art is very difficult to quantify directly; different studies use different evaluation methodologies and metrics when reporting results, making a direct comparison to other systems difficult. Furthermore, in the case of objective metrics, the perceptual relevance and meaning of the reported metrics in most cases is unknown, prohibiting any conclusive insights with respect to the generated audio quality. This dissertation work focuses on: 1. Investigating how effective contemporary metrics are at capturing the audio quality of sounds generated from NAS systems, 2. Assessing the behavior of popularly used embedding distance measures and the embeddings that are used and, 3. Designing metrics that can measure the difference in audio quality between two signals, given that one of them is a reference signal. Thus, the proposed work will focus on developing objective metrics to provide comparable, reproducible and perceptually meaningful audio quality measurement strategies to help set the foundation for future NAS development."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Ph.D."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Towards perceptual metrics for audio quality assessment"]},{"key":"dspace:entity.type","label":"Dspace Entity Type","values":["Publication"]}]}],"canonical_facts":{"dc:contributor.advisor":["Lerch, Alexander"],"dc:contributor.committeemember":["Arthur, Claire","Quinton, Elio","von Coler, Henrik"],"dc:contributor.department":["Music"],"dc:contributor.other":["College of Design","School of Music"],"dc:creator":["Vinay, Ashvala"],"dc:date.accessioned":["2025-01-15T13:48:21Z"],"dc:date.available":["2025-01-15T13:48:21Z"],"dc:date.created":["2024-12"],"dc:date.issued":["2024-08-28"],"dc:date.submitted":["December 2024"],"dc:date.updated":["2025-01-15T13:48:22Z"],"dc:description.abstract":["Recent years have seen considerable advances in audio synthesis with deep generative models known as Neural Audio Synthesizers (NAS). However, the state-of-the-art is very difficult to quantify directly; different studies use different evaluation methodologies and metrics when reporting results, making a direct comparison to other systems difficult. Furthermore, in the case of objective metrics, the perceptual relevance and meaning of the reported metrics in most cases is unknown, prohibiting any conclusive insights with respect to the generated audio quality. This dissertation work focuses on: 1. Investigating how effective contemporary metrics are at capturing the audio quality of sounds generated from NAS systems, 2. Assessing the behavior of popularly used embedding distance measures and the embeddings that are used and, 3. Designing metrics that can measure the difference in audio quality between two signals, given that one of them is a reference signal. Thus, the proposed work will focus on developing objective metrics to provide comparable, reproducible and perceptually meaningful audio quality measurement strategies to help set the foundation for future NAS development."],"dc:description.degree":["Ph.D."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/1853/76868"],"dc:language.iso":["en_US"],"dc:publisher":["Georgia Institute of Technology"],"dc:relation.advisorentity":["1809048a-a767-4f23-ae76-c0eebf261485"],"dc:relation.ispartofseries":["Doctor of Philosophy with a Major in Music Technology"],"dc:relation.orgunit":["c997b6a0-7e87-4a6f-b6fc-932d776ba8d0","92d2daaa-80f2-4d99-b464-ab7c1125fc55"],"dc:relation.seriesentity":["d1fd9079-2e93-4803-98c8-8365a28e0761"],"dc:subject":["Audio Quality Assessment","Sound Quality","Signal Processing"],"dc:title":["Towards perceptual metrics for audio quality assessment"],"dc:type":["Text","Dissertation"],"dspace:entity.type":["Publication"],"thesis:degree_level":["Doctoral"],"thesis:degree_program":["Music Technology"]},"updated_at":"2026-11-19T03:50:26Z"}