TL;DR这篇论文通过建立新的 LibriCSS 数据集并制定一套 Kaldi 基础的 ASR 评估方法,对连续语音分离算法进行了评估和研究,以解决自然对话中语音分离的问题。
Abstract
This paper describes a dataset and protocols for evaluating continuous speech
separation algorithms. Most prior studies on speech separation use
pre-segmented signals of artificially mixed speech utterances which are mostly
\emph{fully} overlapped, and the algorithms are evaluated based on
signal-to-distortion ratio or similar performance metrics. However, i