On The Impact Of Language Familiarity In Talker Change Detection

The ability to detect talker changes when listening to conversational speech is fundamental to the perception and understanding of multi-talker speech. In this paper, we propose a novel experimental paradigm to provide insights on the impact of language familiarity on talker change detection. Two multi-talker speech stimulus sets, one in a language familiar to the listeners (English) and the other unfamiliar (Chinese), are created. A listening test is performed in which listeners indicate the number of talkers in the presented stimuli. Analysis of human performance shows statistically significant results: (a) lower miss (and a higher false alarm) rate in familiar versus unfamiliar language, and (b) larger response time in familiar versus unfamiliar language. These signify a link between perception of talker attributes and language proficiency. Subsequently, a machine system is designed to perform the same task. The system makes use of the current state-of-the-art diarization with x-vector embeddings. A performance comparison indicates machine system falls short of human performance by a huge margin, for both the languages.