Acoustic and linguistic features influence talker change detection Journal Articles uri icon

  •  
  • Overview
  •  
  • Research
  •  
  • Identity
  •  
  • Additional Document Info
  •  
  • View All
  •  

abstract

  • A listening test is proposed in which human participants detect talker changes in two natural, multi-talker speech stimuli sets—a familiar language (English) and an unfamiliar language (Chinese). Miss rate, false-alarm rate, and response times (RT) showed a significant dependence on language familiarity. Linear regression modeling of RTs using diverse acoustic features derived from the stimuli showed recruitment of a pool of acoustic features for the talker change detection task. Further, benchmarking the same task against the state-of-the-art machine diarization system showed that the machine system achieves human parity for the familiar language but not for the unfamiliar language.

authors

  • Sharma, Neeraj Kumar
  • Krishnamohan, Venkat
  • Ganapathy, Sriram
  • Gangopadhayay, Ahana
  • Fink, Lauren

publication date

  • November 1, 2020