Talker Change Detection (TCD): Comparison of human and machine

This study examines human talker change detection (TCD) in multi-party speech utterances using a novel behavioral paradigm in which listeners indicate the moment of perceived talker change. The repository contains the data and codes used in the study.

Publication link:

The Journal of the Acoustical Society of America 145, 131 (2019) https://asa.scitation.org/doi/10.1121/1.5084044?af=R

Popular Press Coverage:

In Inside Science:

https://www.insidescience.org/news/computer-voice-recognition-still-learning-detect-who%E2%80%99s-talking

In ABC News:

https://abcnews.go.com/Technology/research-helping-scientists-understand-humans-recognize-voices-computers/story?id=60699647

Contributors:

Neeraj Kumar Sharma, Shobhana Ganesh, Sriram Ganapathy, Lori L. Holt

Contributors associated with the Carnegie Mellon Univeristy, Pittsburgh and the Indian Institute of Science, Bangalore.

The manuscript is shared here for personal use only. Any other use requires prior permission of the author and the Acoustical Society of America.