Segmental Approaches for Automatic Speaker Verification

Petrovska‐Delacrétaz, Dijana; Černocký, Jaň; Hennebert, Jean; Chollet, G.

doi:10.1006/dspr.2000.0370

Cited by 11 publications

(10 citation statements)

References 24 publications

(25 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, the window is moved and a new estimation is calculated. For each window, a set of coefficients (called predictive coefficients or LPC coefficients) is estimated (see [2,6] for the details of the various algorithms that can be used to estimate the LPC coefficients) and can be used as a parameter vector. Finally, a spectrum envelope can be estimated for the current window from the predictive coefficients.…”

Section: Lpc-based Cepstral Parametersmentioning

confidence: 99%

A Tutorial on Text-Independent Speaker Verification

Bimbot

Bonastre

Fredouille

et al. 2004

EURASIP J. Adv. Signal Process.

Self Cite

639

443

View full text Add to dashboard Cite

This paper presents an overview of a state-of-the-art text-independent speaker verification system. First, an introduction proposes a modular scheme of the training and test phases of a speaker verification system. Then, the most commonly speech parameterization used in speaker verification, namely, cepstral analysis, is detailed. Gaussian mixture modeling, which is the speaker modeling technique used in most systems, is then explained. A few speaker modeling alternatives, namely, neural networks and support vector machines, are mentioned. Normalization of scores is then explained, as this is a very important step to deal with real-world data. The evaluation of a speaker verification system is then detailed, and the detection error trade-off (DET) curve is explained. Several extensions of speaker verification are then enumerated, including speaker tracking and segmentation by speakers. Then, some applications of speaker verification are proposed, including on-site applications, remote applications, applications relative to structuring audio information, and games. Issues concerning the forensic area are then recalled, as we believe it is very important to inform people about the actual performance and limitations of speaker verification systems. This paper concludes by giving a few research trends in speaker verification for the next couple of years.

show abstract

Section: Lpc-based Cepstral Parametersmentioning

confidence: 99%

A Tutorial on Text-Independent Speaker Verification

Bimbot

Bonastre

Fredouille

et al. 2004

EURASIP J. Adv. Signal Process.

Self Cite

639

443

View full text Add to dashboard Cite

show abstract

“…A gender-dependent background model is used and the z-normalization is applied to the likelihood ratio. Since the test segment length is not a priori known, VERE uses a first-order polynomial approximation to compute the mean and standard deviation of the log likelihood ratio of the impostor scores from 3, 10, and 30 s test segments [14].…”

Section: Global Frame-based Systemsmentioning

confidence: 99%

“…The client score for a frame is calculated as a weighted sum of the class-dependent GMM scores, the weights accounting for the probability that the frame belongs to a given class. This approach was evaluated on a subset of the NIST'98 data and was judged disappointing [14,21] as compared to the segmental approaches based on multilayer perceptron (MLP) speaker modeling [13].…”

Section: Segmental Systemsmentioning

confidence: 99%

“…The results obtained at the official evaluation are then analyzed in Section 4. The systems are not described in full detail since most of them are presented in articles specific to each site, published in this volume, which will be refered to whenever necessary [4,6,10,14,15,20]. This article therefore concentrates on the contrastive comparison of the performances.…”

Section: Introductionmentioning

confidence: 97%

See 1 more Smart Citation

The ELISA Systems for the NIST'99 Evaluation in Speaker Detection and Tracking

Nedić¹,

Bimbot²,

Blouet³

et al. 2000

Digital Signal Processing

View full text Add to dashboard Cite

“…ALISP is a data-driven technique that was first developed for very low bit-rate speech coding [6], and then successfully adapted for other tasks such as speaker verification [8] and forgery [19], and language identification [21]. The particularity of ALISP tools is that no textual transcriptions are needed during the learning step, and only raw audio data is sufficient to train the Hidden Markov ALISP models.…”

Section: Introductionmentioning

confidence: 99%

ALISP-Based Data Compression for Generic Audio Indexing

Khemiri

Delacretaz

Chollet

2014

2014 Data Compression Conference

View full text Add to dashboard Cite

In this paper we propose a generic framework to index and retrieve audio. In this framework, audio data is transformed into a sequence of symbols using the ALISP tools. In such a way the audio data is represented in a compact way. Then an approximate matching algorithm inspired from the BLAST technique is exploited to retrieve the majority of audio items that could be present in radio stream. The evaluations of the proposed systems are done on a private radio broadcast database provided by YACAST and other publicly available corpora. The experimental results show an excellent performance in audio identification (for advertisement and songs), audio motif discovery (for advertisement and songs), speaker diarization and laughter detection. Moreover, the ALISP-based system has obtained the best results in ETAPE 2011 (Evaluations en Traitement Automatique de la Parole) evaluation campaign for the speaker diarization task.

show abstract

Segmental Approaches for Automatic Speaker Verification

Cited by 11 publications

References 24 publications

A Tutorial on Text-Independent Speaker Verification

A Tutorial on Text-Independent Speaker Verification

The ELISA Systems for the NIST'99 Evaluation in Speaker Detection and Tracking

ALISP-Based Data Compression for Generic Audio Indexing

Contact Info

Product

Resources

About