DeepAI AI Chat
Log In Sign Up

Speaker Recognition with Cough, Laugh and "Wei"

by   Miao Zhang, et al.

This paper proposes a speaker recognition (SRE) task with trivial speech events, such as cough and laugh. These trivial events are ubiquitous in conversations and less subjected to intentional change, therefore offering valuable particularities to discover the genuine speaker from disguised speech. However, trivial events are often short and idiocratic in spectral patterns, making SRE extremely difficult. Fortunately, we found a very powerful deep feature learning structure that can extract highly speaker-sensitive features. By employing this tool, we studied the SRE performance on three types of trivial events: cough, laugh and "Wei" (a short Chinese "Hello"). The results show that there is rich speaker information within these trivial events, even for cough that is intuitively less speaker distinguishable. With the deep feature approach, the EER can reach 10 despite their extremely short durations (0.2-1.0 seconds).


page 2

page 4


Human and Machine Speaker Recognition Based on Short Trivial Events

Trivial events are ubiquitous in human to human conversations, e.g., cou...

Speaker Recognition using Deep Belief Networks

Short time spectral features such as mel frequency cepstral coefficients...

DeepTalk: Vocal Style Encoding for Speaker Recognition and Speech Synthesis

Automatic speaker recognition algorithms typically characterize speech a...

Full-info Training for Deep Speaker Feature Learning

In recent studies, it has shown that speaker patterns can be learned fro...

A new Speech Feature Fusion method with cross gate parallel CNN for Speaker Recognition

In this paper, a new speech feature fusion method is proposed for speake...

Comparison of Speaker Role Recognition and Speaker Enrollment Protocol for conversational Clinical Interviews

Conversations between a clinician and a patient, in natural conditions, ...

Burstiness Scale: a highly parsimonious model for characterizing random series of events

The problem to accurately and parsimoniously characterize random series ...