Speaker Embedding-aware Neural Diarization: an Efficient Framework for Overlapping Speech Diarization in Meeting Scenarios

TL;DR

This paper introduces SEND, a neural diarization framework that models overlapping speech as a single-label prediction problem, improving efficiency and accuracy in meeting scenarios.

Contribution

The paper reformulates overlapping speech diarization as a single-label prediction task and proposes the SEND framework, achieving state-of-the-art results with fewer parameters.

Findings

Achieves state-of-the-art performance in meeting scenarios

Handles highly overlapped speech without extra initialization

Uses fewer model parameters and lower computational complexity

Abstract

Overlapping speech diarization has been traditionally treated as a multi-label classification problem. In this paper, we reformulate this task as a single-label prediction problem by encoding multiple binary labels into a single label with the power set, which represents the possible combinations of target speakers. This formulation has two benefits. First, the overlaps of target speakers are explicitly modeled. Second, threshold selection is no longer needed. Through this formulation, we propose the speaker embedding-aware neural diarization (SEND) framework, where a speech encoder, a speaker encoder, two similarity scorers, and a post-processing network are jointly optimized to predict the encoded labels according to the similarities between speech features and speaker embeddings. Experimental results show that SEND has a stable learning process and can be trained on highly overlapped data without extra initialization. More importantly, our method achieves the state-of-the-art performance in real meeting scenarios with fewer model parameters and lower computational complexity.