Jayant M. Naik

Speaker verification over long distance telephone lines

The authors present the results of speaker-verification technology development for use over long-distance telephone lines. A description is given of two large speech databases that were collected to support the development of new speaker verification algorithms. Also discussed are the results of discriminant analysis techniques which improve the discrimination between true speakers and imposters. A comparison is made of the performance of two speaker-verification algorithms, one using template-based dynamic time warping, and the other, hidden Markov modeling.<<ETX>>

Fixed text speaker verification method and apparatus

Speaker verification is performed by computing principal components of a fixed text statement comprising a speaker identification code and a two-word phrase, and principal spectral components of a random word phrase. A multi-phrase strategy is utilized in access control to allow successive verification attempts in a single session, if the speaker fails initial attempts. Based upon a verification attempt, the system produces a verification score which is compared with a threshold value. On successive attempts, the criterion for acceptance is changed, and one of a number of criteria must be satisfied for acceptance in subsequent attempts. A speaker normalization function can also be invoked to modify the verification score of persons enrolled with the system who inherently produce scores which result in denial of access. Accuracy of the verification system is enhanced by updating the reference template which then more accurately symbolizes the persons speech signature.

A hybrid HMM-MLP speaker verification algorithm for telephone speech

This paper describes the results of experiments to investigate the integration of MLP (multilayer perceptron) and HMM (hidden Markov modeling) techniques in the task of fixed-text speaker verification. A large speech database collected over the telephone network was used to evaluate the algorithm. Speech data for each speaker was automatically segmented using a supervised HMM-Viterbi decoding scheme and an MLP was trained with this segmented data. The output scores of the MLP, after appropriate scaling were used as observation probabilities in a Viterbi realignment and scoring step. Intra-speaker and inter-speaker scores were generated by training the HMM-MLP system for each speaker and testing against speech data for the same speaker and against all other speakers, who shared utterances of identical text. Our results show that MLP classifiers combined with HMMs improve speaker discrimination by 20% over conventional HMM algorithms for speaker verification.<<ETX>>

Evaluation of a high performance speaker verification system for access control

The results of an extensive evaluation of a speaker verification system for access control are presented. The system employs an algorithm based on the Principal Spectral Components representation derived from the short term spectrum of the speech signal. This system designed for access control applications has been evaluated using a 200 speaker population and a total of over 13,000 true speaker attempts and over 40,000 impostor attempts, both performed on line, over a 4-month period. A true speaker rejection rate of less than 1 % and an impostor acceptance rate of less than 0.1 % have been obtained.

High performance speaker verification using principal spectral components

The described system finds key application in physical entry control and control of access to privileged information. Verification is based on a fast and user-friendly protocol, consisting of two stages: 1. Primary verification using a fixed text phrase. 2. Secondary verification using a random 5-digit sequence. The features used in the verification algorithm are the Principal Spectral Components, derived from the spectrum of the speech signal. Verification experiments on a 40 speaker database give a true speaker rejection rate of less than 1% and an impostor acceptance rate of less than 0.1%.

Laryngeal function: Electroglottograph, ultra‐high‐speed films, and speech inverse filtering

Numerous methods have been devised to assess laryngeal function, including photography, inverse filtering of speech, electroglottography, and others. We have been conducting a series of experiments in which we record simultaneously the electroglottograph (EGG) waveform and the acoustic phonatory signal, while filming vibratory patterns of the vocal folds for both normal subjects and patients with various pathologies and vocal disorders. These data are synchronized via a special timing signal, which is recorded on the audio tape and ultra‐high‐speed laryngeal films. We present graphical plots of this synchronized data including (1) glottal area measured from the films, (2) the EGG waveform, (3) the speech waveform, and (4) the inverse filtered waveform. These results are being used in various ways including the verification that the EGG signal is indicative of the amount of contact between the vocal folds. Other uses of our results are obtaining better models of the source/tract coupling and the synthesis ...