Paper Info
Title
Sub-word unit talker verification using hidden Markov models
Abstract
A talker verification system based on characterizing talker utterances as sequences of subword units represented by hidden Markov models (HMMs) was implemented and tested. Two types of subword units were studied: phonelike units (PLUs) and acoustic segment units (ASUs). PLUs are based on phonetic transcriptions of spoken utterances and ASUs are extracted directly from the acoustic signal without use of any linguistic knowledge. The ASU representation has the advantage of not requiring transcriptions of training utterances. Verification performance was evaluated on a 100-talker database of 20000 isolated digit utterances. The experiments show only small differences in performance between PLU- and ASU-based representations. Overall, the verification equal-error rate is approximately 7 to 8% for one-digit test utterances (approximately 0.5 s in duration) and 1% or less for seven-digit test utterances (approximately 3.5 s in duration). In addition, a technique for updating models, using data from current test utterances, was devised and implemented. Using this adaptation technique, the error rate falls to 6% for one-digit utterances and less than 0.5% for seven-digit utterances. The experiment confirms that excellent verification performance can be obtained using HMMs of subword units
Year
DOI
Venue
1990
10.1109/ICASSP.1990.115621
Albuquerque, NM
Keywords
DocType
ISSN
markov processes,speech recognition,acoustic segment units,adaptation technique,error rate,hidden markov models,isolated digit utterances,phonelike units,phonetic transcriptions,subword units,talker utterances,talker verification system,verification equal-error rate,robustness,hidden markov model,system testing,security,telephony,databases
Conference
1520-6149
Citations 
PageRank 
References 
37
29.59
9
Authors
3
Name
Order
Citations
PageRank
Rosenberg, A.E.13729.59
Chin-Hui Lee23731.62
frank k soong3460194.71