ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 5 Jun 2024.
Builds on
18 of 31 references.
References · 18
- 2019pyannote.audio: neural building blocks for speaker diarizationcited by 175
- 2020LibriMix: An Open-Source Dataset for Generalizable Speech Separationcited by 154
- 2021A Review of Speaker Diarization: Recent Advances with Deep Learningcited by 122
- 2019End-to-End Neural Speaker Diarization with Self-attentioncited by 74
- 2020Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard taskscited by 69
- 2021M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challengecited by 67
- 2021AISHELL-4: An Open Source Dataset for Speech Enhancement, Separation, Recognition and Speaker Diarization in Conference Scenariocited by 58
- 2018gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Accelerationcited by 46
- 2019Overlap-aware diarization: resegmentation using neural end-to-end overlapped speech detectioncited by 26
- 2021Encoder-Decoder Based Attractors for End-to-End Neural Diarizationcited by 20
- 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 18
- 2019End-to-end Domain-Adversarial Voice Activity Detectioncited by 11
6 more
- 2020Analysis of the BUT Diarization System for VoxConverse Challengecited by 11
- 2022GPU-accelerated Guided Source Separation for Meeting Transcriptioncited by 10
- 2022Overlapped speech and gender detection with WavLM pre-trained featurescited by 6
- 2021Self-Attention Channel Combinator Frontend for End-to-End Multichannel Far-field Speech Recognitioncited by 4
- 2021Learning Filterbanks for End-to-End Acoustic Beamformingcited by 1
- 2024Channel-Combination Algorithms for Robust Distant Voice Activity and Overlapped Speech Detectioncited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.