The NIST 1999 Speaker Recognition Evaluation—An Overview

Martín, Alvin F.; Przybocki, Mark A.

doi:10.1006/dspr.1999.0355

Cited by 121 publications

(77 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Like the EM algorithm, the adaption is a two step estimation process. The first step is identical to the expectation step of the EM algorithm, where estimates of the sufficient statistics 7 of the speaker's training data are computed for each mixture in the UBM. Unlike the second step of the EM algorithm, for adaptation these new sufficient statistic estimates are then combined with the old sufficient statistics from the UBM mixture parameters using a data-dependent mixing coefficient.…”

Section: Adaptation Of Speaker Modelmentioning

confidence: 99%

“…We use the term Bayesian adaptation since, as applied to the speaker-independent UBM to estimate the speaker-dependent model, the operation closely resembles speaker adaptation used in speech recognition applications. 7 These are the basic statistics needed to be estimated to compute the desired parameters. For a GMM mixture, these are the count and the first and second moments required to compute the mixture weight, mean, and variance.…”

Section: Adaptation Of Speaker Modelmentioning

confidence: 99%

“…A speech segment is then labeled by selecting the most likely model (CARB or ELEC) based on the models' likelihood values. This handset detector has been used by NIST to supply handset information to SRE participants as well as for analysis of results [7].…”

Section: Handset Score Normalizationmentioning

confidence: 99%

“…These systems, fielded by different sites, have consistently produced state-of-the-art performance [6,7]. In particular, a GMM-based system developed by MIT Lincoln Laboratory [8], employing Bayesian adaptation of speaker models from a universal background model and handset-based score normalization, has been the basis of the top performing systems in the NIST SREs since 1996.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Speaker Verification Using Adapted Gaussian Mixture Models

Reynolds

Quatieri

Dunn

2000

Digital Signal Processing

3,710

2,376

View full text Add to dashboard Cite

In this paper we describe the major elements of MIT Lincoln Laboratory's Gaussian mixture model (GMM)-based speaker verification system used successfully in several NIST Speaker Recognition Evaluations (SREs). The system is built around the likelihood ratio test for verification, using simple but effective GMMs for likelihood functions, a universal background model (UBM) for alternative speaker representation, and a form of Bayesian adaptation to derive speaker models from the UBM. The development and use of a handset detector and score normalization to greatly improve verification performance is also described and discussed. Finally, representative performance benchmarks and system behavior experiments on NIST SRE corpora are presented.

show abstract

Section: Adaptation Of Speaker Modelmentioning

confidence: 99%

Section: Adaptation Of Speaker Modelmentioning

confidence: 99%

Section: Handset Score Normalizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Speaker Verification Using Adapted Gaussian Mixture Models

Reynolds

Quatieri

Dunn

2000

Digital Signal Processing

3,710

2,376

View full text Add to dashboard Cite

show abstract

“…Fundamental frequency estimation is an essential requirement in systems for pitchsynchronous analysis, speech analysis/synthesis and speech coding. It has been reported that fundamental frequency can improve performance of a speech recognition system for a tonal language [4] and of a speaker identification system [5]. These formants correspond closely to the acoustic resonance frequencies created by a speaker's vocal tract and carry unique information specific to the speaker [6].…”

Section: Introductionmentioning

confidence: 99%

Text-Independent Speaker Identification Using Vowel Formants

Almaadeed

Aggoun

Amira

2015

J Sign Process Syst

View full text Add to dashboard Cite

Automatic speaker identification has become a challenging research problem due to its wide variety of applications. Neural networks and audio-visual identification systems can be very powerful, but they have limitations related to the number of speakers. The performance drops gradually as more and more users are registered with the system. This paper proposes a scalable algorithm for real-time text-independent speaker identification based on vowel recognition. Vowel formants are unique across different speakers and reflect the vocal tract information of a particular speaker. The contribution of this paper is the design of a scalable system based on vowel formant filters and a scoring scheme for classification of an unseen instance. Mel-Frequency Cepstral Coefficients (MFCC) and Linear Predictive Coding (LPC) have both been analysed for comparison to extract vowel formants by windowing the given signal. All formants are filtered by known formant frequencies to separate the vowel formants for further processing. The formant frequencies of each speaker are collected during the training phase. A test signal is also processed in the same way to find vowel formants and compare them with the saved vowel formants to identify the speaker for the current signal. A score-based scheme allows the speaker with the highest matching formants to own the current signal. This model requires less than 100 bytes of data to be saved for each speaker to be identified, and can identify the speaker within a second. Tests conducted on multiple databases show that this score-based scheme outperforms the back propagation neural network and Gaussian mixture models. Usually, the longer the speech files, the more significant were the improvements in accuracy.

show abstract