2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

Technical Program

Paper Detail

Paper IDSPE-54.1
Paper Title END-TO-END DIARIZATION FOR VARIABLE NUMBER OF SPEAKERS WITH LOCAL-GLOBAL NETWORKS AND DISCRIMINATIVE SPEAKER EMBEDDINGS
Authors Soumi Maiti, CUNY, United States; Hakan Erdogan, Kevin Wilson, Scott Wisdom, Google, United States; Shinji Watanabe, Johns Hopkins University, United States; John R. Hershey, Google, United States
SessionSPE-54: End-to-End Speaker Diarization and Recognition
LocationGather.Town
Session Time:Friday, 11 June, 13:00 - 13:45
Presentation Time:Friday, 11 June, 13:00 - 13:45
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
Abstract We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling speaker overlap and enabling straightforward handling of discriminative training, unlike traditional clustering-based diarization methods. The proposed system is designed to handle meetings with unknown numbers of speakers, using variable-number permutation-invariant cross-entropy based loss functions. We introduce several components that appear to help with diarization performance, including a local convolutional network followed by a global self-attention module, multi-task transfer learning using a speaker identification component, and a sequential approach where the model is refined with a second stage. These are trained and validated on simulated meeting data based on LibriSpeech and LibriTTS datasets; final evaluations are done using LibriCSS, which consists of simulated meetings recorded using real acoustics via loudspeaker playback. The proposed model performs better than previously proposed end-to-end diarization models on these data.