Asobo: Attentive Beamformer Selection For Distant Speaker Diarization In Meetings
2024 · Theo Mariotte, Anthony Larcher, Silvio Montresor, et al.
Abstract
Speaker Diarization (SD) aims at grouping speech segments that belong to the same speaker. This task is required in many speech-processing applications, such as rich meeting transcription. In this context, distant microphone arrays usually capture the audio signal. Beamforming, i.e., spatial filtering, is a common practice to process multi-microphone audio data. However, it often requires an explicit localization of the active source to steer the filter. This paper proposes a self-attention-based algorithm to select the output of a bank of fixed spatial filters. This method serves as a feature extractor for joint Voice Activity (VAD) and Overlapped Speech Detection (OSD). The speaker diarization is then inferred from the detected segments. The approach shows convincing distant VAD, OSD, and SD performance, e.g. 14.5% DER on the AISHELL-4 dataset. The analysis of the self-attention weights demonstrates their explainability, as they correlate with the speaker's angular locations.
Authors
(none)
Tags
Stats
Related papers
- Multi-microphone Automatic Speech Segmentation In Meetings Based On Circular Harmonics Features (2023)0.00
- Exploring Speaker-related Information In Spoken Language Understanding For Better Speaker Diarization (2023)0.00
- Joint Beamforming And Speaker-attributed ASR For Real Distant-microphone Meeting Transcription (2024)2.26
- Audio-visual Speaker Diarization Based On Spatiotemporal Bayesian Fusion (2016)14.51
- Target-speaker Voice Activity Detection: A Novel Approach For Multi-speaker Diarization In A Dinner Party Scenario (2020)16.19
- One Model To Rule Them All ? Towards End-to-end Joint Speaker Diarization And Speech Recognition (2023)9.59
- Speaker Diarisation Using 2D Self-attentive Combination Of Embeddings (2019)9.92
- Speaker Embeddings With Weakly Supervised Voice Activity Detection For Efficient Speaker Diarization (2024)2.26