# Neural Multichannel Distant Speaker Diarization with Heavy-tailed Source Separation Model

arXiv: https://arxiv.org/abs/2609.12154 · HTML: https://mlsanity.com/paper/2609.12154/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 36 references that are in the map.
- First posted on arXiv 10 Sep 2026.

## Builds on (most cited first, 20 of 20)

- [Semi-Supervised Learning with Deep Generative Models](https://mlsanity.com/paper/1406.5298/) (2014)
- [CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings](https://mlsanity.com/paper/2004.09249/) (2020)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [Bayesian HMM clustering of x-vector sequences (VBx) in speaker diarization: theory, implementation and analysis on standard tasks](https://mlsanity.com/paper/2012.14952/) (2020)
- [M2MeT: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge](https://mlsanity.com/paper/2110.07393/) (2021)
- [A Recurrent Variational Autoencoder for Speech Enhancement](https://mlsanity.com/paper/1910.10942/) (2019)
- [Encoder-Decoder Based Attractors for End-to-End Neural Diarization](https://mlsanity.com/paper/2106.10654/) (2021)
- [DiarizationLM: Speaker Diarization Post-Processing with Large Language Models](https://mlsanity.com/paper/2401.03506/) (2024)
- [SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models](https://mlsanity.com/paper/2508.06372/) (2025)
- [EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers](https://mlsanity.com/paper/2203.17068/) (2022)
- [The CHiME-8 DASR Challenge for Generalizable and Array Agnostic Distant Automatic Speech Recognition and Diarization](https://mlsanity.com/paper/2407.16447/) (2024)
- [Neural Blind Source Separation and Diarization for Distant Speech Recognition](https://mlsanity.com/paper/2406.08396/) (2024)
- [Surrogate Source Model Learning for Determined Source Separation](https://mlsanity.com/paper/2011.05540/) (2020)
- [Multi-Channel End-to-End Neural Diarization with Distributed Microphones](https://mlsanity.com/paper/2110.04694/) (2021)
- [FastMVAE2: On improving and accelerating the fast variational autoencoder-based source separation algorithm for determined mixtures](https://mlsanity.com/paper/2109.13496/) (2021)
- [Neural Fast Full-Rank Spatial Covariance Analysis for Blind Source Separation](https://mlsanity.com/paper/2306.10240/) (2023)
- [Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation](https://mlsanity.com/paper/2205.05330/) (2022)
- [ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings](https://mlsanity.com/paper/2406.03251/) (2024)
- [Can We Really Repurpose Multi-Speaker ASR Corpus for Speaker Diarization?](https://mlsanity.com/paper/2507.09226/) (2025)
- [Neural Multichannel Distant Speaker Diarization and Source Separation with Beta Speaker Activity Prior](https://mlsanity.com/paper/2608.28661/) (2026)

## Abstract (arXiv)

Distant speaker diarization remains challenging due to difficult acoustic environments, varying numbers of speakers and overlapping speech. Model-driven methods are proposed to exploit the speech source features in multi-channel recordings that help diarization. This paper generalizes a neural model that jointly learns to perform blind source separation and diarization over speech mixtures (neural FCASA) with heavy-tailed models. The popular Gaussian distribution has been applied for variance modeling in the original source separation model, which we replace with two families of heavy-tailed models (Leptokurtic Generalized Gaussian distribution and Student's t distribution) to better capture the heavy-tailedness in speech signals. Thanks to the Gaussian scale mixture model, we are able to unify the proposed method and the original one under the same form of learning objective. Our experiments show consistent large improvements in Diarization Error Rate (DER) and Jaccard Error Rate (JER) compared to the baseline on various corpora.