Looking to listen at the cocktail party

• Material Type: 記事
• Title: Looking to listen at the cocktail party
• Author Heading: Ariel Ephrat; Inbar Mosseri; Oran Lang; Tali Dekel; Kevin Wilson; Avinatan Hassidim; William T. Freeman; Michael Rubinstein
• Publication Date: 2018-07-30
• Publication Date (W3CDTF): 2018-07-30
• Alternative Title: a speaker-independent audio-visual model for speech separation
• Periodical title: ACM Transactions on Graphics
• No. or year of volume/issue: 37 4
• Volume: 37
• Issue: 4
• Pages: 1-11
• Publication date of volume/issue (W3CDTF): 2018-07-30
• ISSN (Periodical Title): 07300301
• Publication (Periodical Title): Association for Computing Machinery (ACM)
• Target Audience: 一般
• DOI: 10.1145/3197517.3201357
• Date Created (W3CDTF): 2018-07-31
• Rights (production): http://www.acm.org/publications/policies/copyright_policy#Background
• Related Material (URI): https://dl.acm.org/doi/pdf/10.1145/3197517.3201357
• Is Referenced By: Audio-Visual Model for Generating Eating Sounds Using Food ASMR Videos; https://cir.nii.ac.jp/crid/1360009142696887296; Do We Need Sound for Sound Source Localization?; https://cir.nii.ac.jp/crid/1360009142866227072; A genotype imputation method for de-identified haplotype reference information by using recurrent neural network; https://cir.nii.ac.jp/crid/1360290617586358016; 音源分離技術の基礎と動向; https://cir.nii.ac.jp/crid/1390295658299596928; Developing AI that Pays Attention to Who You Want to Listen to: Deep-learning-based Selective Hearing with SpeakerBeam; https://cir.nii.ac.jp/crid/1390295679775873280; Speaker-Independent Audio-Visual Speech Separation Based on Transformer in Multi-Talker Environments; https://cir.nii.ac.jp/crid/1390573242790286336
• Data Provider (Database): 国立情報学研究所 : CiNii Research
• Original Data Provider (Database): Crossref; https://www.crossref.org

• Summary, etc.: <jats:p> We present a joint audio-visual model for isolating a single speech signal from a mixture of sounds such as other speakers and ba...