Existing approaches have used several feature extraction methods that have been adopted directly from the speech recognition task.However, the nature of these two tasks is contradictory given that speaker variability is one of the major error sources in speech recognition whereas in speaker recognition, it is the information that we wish to extract.This study addresses this issue by specifying the most speaker-specific features and trying to further improve the system configuration for obtaining a representation of the auditory features with lower dimensionality.Tags: File Transfer Protocol Research PaperSusan Anker Real EssaysTwo Essays Chief And GreedProblem Solving In CCritical Analytical ThinkingConclusion In A Research PaperNo Essay College ScholarshipNuclear Weapons Should Be Banned Essay
Speaker identification (SID) aims to identify the underlying speaker(s) given a speech utterance.
In a speaker identification system, the first component is the front-end or feature extractor.
In this thesis, the possible benefits of adapting a biologically-inspired model of human auditory processing as part of the front-end of a SID system are examined.
This auditory model named Auditory Image Model (AIM) generates the stabilized auditory image (SAI).
During my first year as a Ph D student, I met Honza Černocký, who had supervised Petr Schwarz’s thesis, and I started co-operating with his group fully.
That resulted in a year-long internship together with Peter at the Oregon Graduate Institute (OGI), US, which was supervised by world-renowned Hynek Heřmanský.
Thanks to automatization, I also got to speaker voice recognition, which became the topic of my thesis.
I met the Phonexia co-founder Petr thanks to the fact too, as I often needed to consult him about using techniques I wanted to add to mine. The offer of innovative projects, travelling, internships and working abroad was very alluring, in addition to sparing me the one year of military service.
What we managed to do within that one year was almost unbelievable.
And then, in 2003 and still under the auspices of OGI, we first introduced ourselves to the worldwide speech-recognition community.