Towards Neural Diarization For Unlimited Numbers Of Speakers Using Global And Local Attractors

Abstract

Attractor-based end-to-end diarization is achieving comparable accuracy to the carefully tuned conventional clustering-based methods on challenging datasets. However, the main drawback is that it cannot deal with the case where the number of speakers is larger than the one observed during training. This is because its speaker counting relies on supervised learning. In this work, we introduce an unsupervised clustering process embedded in the attractor-based end-to-end diarization. We first split a sequence of frame-wise embeddings into short subsequences and then perform attractor-based diarization for each subsequence. Given subsequence-wise diarization results, inter-subsequence speaker correspondence is obtained by unsupervised clustering of the vectors computed from the attractors from all the subsequences. This makes it possible to produce diarization results of a large number of speakers for the whole recording even if the number of output speakers for each subsequence is limited

Stats

• citations31
• S2 citations—
• github stars0
• HF likes0
• heat score11.29
• arxiv keyhoriguchi2021towards

Related papers

• Online Neural Diarization Of Unlimited Numbers Of Speakers Using Global And Local Attractors (2022)10.07
• Encoder-decoder Based Attractors For End-to-end Neural Diarization (2021)13.05
• End-to-end Diarization For Variable Number Of Speakers With Local-global Networks And Discriminative Speaker Embeddings (2021)0.00
• Frame-wise Streaming End-to-end Speaker Diarization With Non-autoregressive Self-attention-based Attractors (2023)2.26
• End-to-end Speaker Diarization As Post-processing (2020)11.08
• Multi-target Extractor And Detector For Unknown-number Speaker Diarization (2022)8.09
• Improving End-to-end Neural Diarization Using Conversational Summary Representations (2023)0.00
• Do End-to-end Neural Diarization Attractors Need To Encode Speaker Characteristic Information? (2024)2.26