서브메뉴
검색
Unsupervised Sound Separation
Unsupervised Sound Separation
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102838
- ISBN
- 9798314843314
- DDC
- 004
- 서명/저자
- Unsupervised Sound Separation
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 215 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
- 주기사항
- Advisor: Smaragdis, Paris.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
- 초록/해제
- 요약In this thesis, we tackle the problem of training a machine to perceive, disentangle and reconstruct independent source waveforms from a given mixture audio recording without the need of explicit supervision. The problem becomes even more apparent with current state-of-the-art approaches which are largely dependent on the existence of vast amounts of carefully curated data. In essence, this thesis presents a holistic approach on how people can develop sound separation algorithms based on neural networks which are able to scale up to multiple users, modalities and datasets without the need of annotated data. To that end, the contributions of this thesis is threefold. The first part of the thesis describes novel unsupervised and self-supervised algorithms for sound source separation problems under a wide spectrum of environmental setups. The second part aims to expand the applicability of sound separation systems using external condition information (e.g. video, text and other semantic discriminative concepts) which consists of the multi-modal aspect of this work. Finally, the last chapter presents potential obstacles towards the deployment of the aforementioned algorithms (e.g. scarcity of labels, lack of data on the same device during training, limited computational resources, reluctance of the users to share their private data, erroneous predictions, etc.) as well as proposes novel solutions which can be seamlessly integrated into their real-world implementations.
- 일반주제명
- Computer science
- 일반주제명
- Engineering
- 일반주제명
- Information technology
- 키워드
- Sound separation
- 기타저자
- University of Illinois at Urbana-Champaign Computer Science
- 기본자료저록
- Dissertations Abstracts International. 86-11B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365851
■00520260209102838
■006m o d
■007cr#unu||||||||
■020 ▼a9798314843314
■035 ▼a(MiAaPQ)AAI32063754
■035 ▼a(MiAaPQ)httphdlhandlenet2142120294
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aTzinis, Efthymios.
■24510▼aUnsupervised Sound Separation
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a215 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 86-11, Section: B.
■500 ▼aAdvisor: Smaragdis, Paris.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
■520 ▼aIn this thesis, we tackle the problem of training a machine to perceive, disentangle and reconstruct independent source waveforms from a given mixture audio recording without the need of explicit supervision. The problem becomes even more apparent with current state-of-the-art approaches which are largely dependent on the existence of vast amounts of carefully curated data. In essence, this thesis presents a holistic approach on how people can develop sound separation algorithms based on neural networks which are able to scale up to multiple users, modalities and datasets without the need of annotated data. To that end, the contributions of this thesis is threefold. The first part of the thesis describes novel unsupervised and self-supervised algorithms for sound source separation problems under a wide spectrum of environmental setups. The second part aims to expand the applicability of sound separation systems using external condition information (e.g. video, text and other semantic discriminative concepts) which consists of the multi-modal aspect of this work. Finally, the last chapter presents potential obstacles towards the deployment of the aforementioned algorithms (e.g. scarcity of labels, lack of data on the same device during training, limited computational resources, reluctance of the users to share their private data, erroneous predictions, etc.) as well as proposes novel solutions which can be seamlessly integrated into their real-world implementations.
■590 ▼aSchool code: 0090.
■650 4▼aComputer science
■650 4▼aEngineering
■650 4▼aInformation technology
■653 ▼aSound separation
■653 ▼aAudio-visual perception
■653 ▼aUnsupervised learning
■653 ▼aSelf-supervised learning
■653 ▼aSpeech enhancement
■653 ▼aEfficient neural networks
■653 ▼aFederated learning
■690 ▼a0984
■690 ▼a0489
■690 ▼a0800
■690 ▼a0537
■71020▼aUniversity of Illinois at Urbana-Champaign▼bComputer Science.
■7730 ▼tDissertations Abstracts International▼g86-11B.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365851▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
