Reformulating DOVER-Lap Label Mapping as a Graph Partitioning Problem

TL;DR

This paper reformulates the label mapping in DOVER-Lap as a graph partitioning problem, analyzes its computational complexity, proposes a more efficient algorithm, and demonstrates its effectiveness on the AMI corpus.

Contribution

It introduces a graph partitioning framework for DOVER-Lap label mapping, proposes a tractable approximation algorithm, and provides theoretical bounds and empirical validation.

Findings

DOVER-Lap label mapping is exponential in input size.

Proposed a computationally tractable modification of DOVER's label mapping.

Empirically validated methods on the AMI meeting corpus.

Abstract

We recently proposed DOVER-Lap, a method for combining overlap-aware speaker diarization system outputs. DOVER-Lap improved upon its predecessor DOVER by using a label mapping method based on globally-informed greedy search. In this paper, we analyze this label mapping in the framework of a maximum orthogonal graph partitioning problem, and present three inferences. First, we show that DOVER-Lap label mapping is exponential in the input size, which poses a challenge when combining a large number of hypotheses. We then revisit the DOVER label mapping algorithm and propose a modification which performs similar to DOVER-Lap while being computationally tractable. We also derive an approximation bound for the algorithm in terms of the maximum number of hypotheses speakers. Finally, we describe a randomized local search algorithm which provides a near-optimal $(1-\epsilon)$-approximate solution to the problem with high probability. We empirically demonstrate the effectiveness of our methods on the AMI meeting corpus. Our code is publicly available: https://github.com/desh2608/dover-lap.