Frame-wise and overlap-robust speaker embeddings for meeting diarization

2023/06/01 by Cord-Landwehr, Tobias, Boeddeker, Christoph, Zorilă, Cătălin +2 · 1 citation
#Audio and Speech Processing (eess.AS) #FOS: Electrical engineering #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2306.00625

Abstract

Using a Teacher-Student training approach we developed a speaker embedding extraction system that outputs embeddings at frame rate. Given this high temporal resolution and the fact that the student produces sensible speaker embeddings even for segments with speech overlap, the frame-wise embeddings serve as an appropriate representation of the input speech signal for an end-to-end neural meeting diarization (EEND) system. We show in experiments that this representation helps mitigate a well-known problem of EEND systems: when increasing the number of speakers the diarization performance drop is significantly reduced. We also introduce block-wise processing to be able to diarize arbitrarily long meetings.

Cited by

• Synthesizing speech with selected perceptual voice qualities - A case study with creaky voice

Related

• Geodesic interpolation of frame-wise speaker embeddings for the diarization of meeting scenarios
• End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification
• Utterance-by-utterance overlap-aware neural diarization with Graph-PIT
• Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios
• Leveraging Speaker Embeddings in End-to-End Neural Diarization for Two-Speaker Scenarios