Talker change detection: A comparison of human and machine performance

Sharma, Neeraj Kumar and Ganesh, Shobhana and Ganapathy, Sriram and Holt, Lori L (2019) Talker change detection: A comparison of human and machine performance. In: JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 145 (1). pp. 131-142.

PDF Jou_Aco_Soc_Ame_145-1_131_2019.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

The automatic analysis of conversational audio remains difficult, in part, due to the presence of multiple talkers speaking in turns, often with significant intonation variations and overlapping speech. The majority of prior work on psychoacoustic speech analysis and system design has focused on single-talker speech or multi-talker speech with overlapping talkers (for example, the cocktail party effect). There has been much less focus on how listeners detect a change in talker or in probing the acoustic features significant in characterizing a talker's voice in conversational speech. This study examines human talker change detection (TCD) in multi-party speech utterances using a behavioral paradigm in which listeners indicate the moment of perceived talker change. Human reaction times in this task can be well-estimated by a model of the acoustic feature distance among speech segments before and after a change in talker, with estimation improving for models incorporating longer durations of speech prior to a talker change. Further, human performance is superior to several online and offline state-of-the-art machine TCD systems. (C) 2019 Acoustical Society of America.

Item Type:	Journal Article
Publication:	JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA
Publisher:	ACOUSTICAL SOC AMER AMER INST PHYSICS
Additional Information:	Copyright of this article belongs to ACOUSTICAL SOC AMER AMER INST PHYSICS
Department/Centre:	Division of Electrical Sciences > Electrical Engineering
Date Deposited:	21 Feb 2019 04:50
Last Modified:	21 Feb 2019 04:50
URI:	http://eprints.iisc.ac.in/id/eprint/61774

Actions (login required)

View Item