Towards Lifelong Human Assisted Speaker Diarization

Meysam Shamsi (1) , Anthony Larcher (1, 2) , Loïc Barrault (1) , Sylvain Meignier (1) , Yevheni Prokopalo , Marie Tahon (1) , Ambuj Mehrish (1) , Simon Petitrenaud (1) , Olivier Galibert (3) , Samuel Gaist (4) , André Anjos (4) , Sébastien Marcel (4) , Marta Costa-Jussà

1 LIUM - Laboratoire d'Informatique de l'Université du Mans
2 Institut Informatique Claude Chappe
3 LNE - Laboratoire National de Métrologie et d’Essais
4 IDIAP Research Institute

This paper introduces the resources necessary to develop and evaluate human assisted lifelong learning speaker diarization systems. It describes the ALLIES corpus and associated protocols, especially designed for diarization of a collection audio recordings across time. This dataset is compared to existing corpora and the performances of three baseline systems, based on x-vectors, i-vectors and VBxHMM, are reported for reference. Those systems are then extended to include an active correction process that efficiently guides a human annotator to improve the automatically generated hypotheses. An open-source simulated human expert is provided to ensure reproducibility of the human assisted correction process and its fair evaluation. An exhaustive evaluation, of the human assisted correction shows the high potential of this approach. The ALLIES corpus, a baseline system including the active correction module and all evaluation tools are made freely available to the scientific community.

Mots clés: Speaker diarization; Lifelong learning; Human assisted learning; Evaluation; human assisted learning; evaluation

Domaines: Informatique [cs]

Meysam Shamsi, Anthony Larcher, Loïc Barrault, Sylvain Meignier, Yevheni Prokopalo, et al.. Towards Lifelong Human Assisted Speaker Diarization. Computer Speech and Language, 2023, 77, pp.101437. ⟨10.1016/j.csl.2022.101437⟩. ⟨hal-03737796⟩