Self-supervised learning approaches have lately achieved great success on a broad spectrum of machine learning problems. In the field of speech processing, one of the most successful recent self-supervised models is wav2vec 2.0. In this paper, we explore the effectiveness of this model on three basic speech classification tasks: speaker change detection, overlapped speech detection, and voice activity detection. First, we concentrate on only one task -- speaker change detection -- where our proposed system surpasses the previously reported results on four different corpora, and achieves comparable performance even when trained on out-of-domain data from an artificially designed dataset. Then we expand our approach to tackle all three tasks in a single multitask system with state-of-the-art performance on the AMI corpus. The implementation of the algorithms in this paper is publicly available at https://github.com/mkunes/w2v2_audioFrameClassification.

翻译：自监督学习方法近期在广泛的机器学习问题中取得了巨大成功。在语音处理领域，最成功的近期自监督模型之一是wav2vec 2.0。本文探讨了该模型在三种基本语音分类任务上的有效性：说话人变化检测、重叠语音检测和语音活动检测。首先，我们专注于单一任务——说话人变化检测，在该任务中，我们提出的系统在四个不同语料库上超越了先前报告的结果，即使在使用人工设计数据集的域外数据进行训练时，也能达到可比的性能。随后，我们扩展方法以在一个多任务系统中同时处理所有三个任务，并在AMI语料库上取得了最先进的性能。本文中算法的实现已在https://github.com/mkunes/w2v2_audioFrameClassification 公开提供。