Towards lifelong human assisted speaker diarization. (January 2023)

• Record Type: Journal Article
• Authors: Shamsi, Meysam; Larcher, Anthony; Barrault, Loic; Meignier, Sylvain; Prokopalo, Yevheni; Tahon, Marie; Mehrish, Ambuj; Petitrenaud, Simon; Galibert, Olivier; Gaist, Samuel; Anjos, André; Marcel, Sebastien; Costa-jussà, Marta R.
• Is Part Of: Computer speech & language. Volume 77(2023)
• Publication Date: 2023-01
• Subjects: Speaker diarization -- Lifelong learning -- Human assisted learning -- Evaluation; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2022.101437
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: 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. Highlights: We provide resources to develop human assisted lifelong learning diarization. New metrics to evaluate human-assisted lifelong learning diarization are introduced. We mark a step forward of the human assisted lifelong learning diarization system.