Technical Program

Paper Detail

Paper IDSPE-P5.2
Paper Title FRAME-LEVEL PHONEME-INVARIANT SPEAKER EMBEDDING FOR TEXT-INDEPENDENT SPEAKER RECOGNITION ON EXTREMELY SHORT UTTERANCES
Authors Naohiro Tawara, Atsunori Ogawa, Tomoharu Iwata, Marc Delcroix, NTT Communication Science Laboratories, Japan; Tetsuji Ogawa, Waseda University, Japan
SessionSPE-P5: Deep Speaker Recognition Models
LocationOn-Demand
Session Time:Wednesday, 06 May, 09:00 - 11:00
Presentation Time:Wednesday, 06 May, 09:00 - 11:00
Presentation Poster
Topic Speech Processing: [SPE-SPKR] Speaker Recognition and Characterization
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Virtual Presentation  Click here to watch in the Virtual Conference