# Collar-aware Training for Streaming Speaker Change Detection in Broadcast Speech

arXiv: https://arxiv.org/abs/2205.07086 · HTML: https://mlsanity.com/paper/2205.07086/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 14 May 2022.

## Builds on (most cited first, 12 of 12)

- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [End-to-End Neural Speaker Diarization with Permutation-Free Objectives](https://mlsanity.com/paper/1909.05952/) (2019)
- [End-to-end speaker segmentation for overlap-aware resegmentation](https://mlsanity.com/paper/2104.04045/) (2021)
- [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)
- [The Third DIHARD Diarization Challenge](https://mlsanity.com/paper/2012.01477/) (2020)
- [CN-CELEB: a challenging Chinese speaker recognition dataset](https://mlsanity.com/paper/1911.01799/) (2019)
- [Building and Evaluation of a Real Room Impulse Response Dataset](https://mlsanity.com/paper/1811.06795/) (2018)
- [Overlap-aware low-latency online speaker diarization based on end-to-end local segmentation](https://mlsanity.com/paper/2109.06483/) (2021)
- [Third DIHARD Challenge Evaluation Plan](https://mlsanity.com/paper/2006.05815/) (2020)
- [DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding](https://mlsanity.com/paper/2105.13802/) (2021)

## Abstract (arXiv)

In this paper, we present a novel training method for speaker change detection models. Speaker change detection is often viewed as a binary sequence labelling problem. The main challenges with this approach are the vagueness of annotated change points caused by the silences between speaker turns and imbalanced data due to the majority of frames not including a speaker change. Conventional training methods tackle these by artificially increasing the proportion of positive labels in the training data. Instead, the proposed method uses an objective function which encourages the model to predict a single positive label within a specified collar. This is done by marginalizing over all possible subsequences that have exactly one positive label within the collar. Experiments on English and Estonian datasets show large improvements over the conventional training method. Additionally, the model outputs have peaks concentrated to a single frame, removing the need for post-processing to find the exact predicted change point which is particularly useful for streaming applications.