PRISM: Pre-trained Indeterminate Speaker Representation Model for Speaker Diarization and Speaker Verification

TL;DR

This paper introduces PRISM, a pre-trained indeterminate speaker representation model that dynamically adjusts speaker embeddings based on context, improving performance in verification, clustering, and diarization tasks.

Contribution

The paper presents a novel indeterminate speaker embedding approach that considers context and content, enhancing accuracy over traditional fixed-vector methods.

Findings

Significant improvements in speaker verification accuracy.

Enhanced clustering and diarization performance.

Effective adaptation of the model to various downstream tasks.

Abstract

Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as fixed vectors in high-dimensional space. This could lead to biased estimations, especially when handling shorter utterances. In this paper we propose to represent a speaker utterance as "floating" vector whose state is indeterminate without knowing the context. The state of a speaker representation is jointly determined by itself, other speech from the same speaker, as well as other speakers it is being compared to. The content of the speech also contributes to determining the final state of a speaker representation. We pre-train an indeterminate speaker representation model that estimates the state of an utterance based on the context. The pre-trained model can be fine-tuned for downstream tasks such as speaker verification, speaker clustering, and speaker diarization. Substantial improvements are observed across all downstream tasks.