End-to-end diarization for variable number of speakers with local-global networks and discriminative speaker embeddings

Soumi Maiti*, Hakan Erdogan, Kevin Wilson, Scott Wisdom, Shinji Watanabe, John R. Hershey

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

14 Citations (Scopus)


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, multitask 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.

Original languageEnglish
Pages (from-to)7183-7187
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Publication statusPublished - 2021
Externally publishedYes
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 2021 Jun 62021 Jun 11


  • Attention
  • Deep learning
  • Diarization

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering


Dive into the research topics of 'End-to-end diarization for variable number of speakers with local-global networks and discriminative speaker embeddings'. Together they form a unique fingerprint.

Cite this