A new nonlinear feature extraction algorithm for speaker verification

Chétouani, Mohamed; Gas, Bruno; Zarader, Jean-Luc; Faundez-Zanuy, Marcos

doi:10.21437/interspeech.2004-500

Cited by 7 publications

(2 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A Similar approach is used in [98] and [104] for speaker verification. Inspired by the Linear Predictive Coding (LPC) of speech, a nonlinear extension of LPC is proposed as Neural Predictive Coding in [105] where speaker-dependent speech features are discriminatively learned in a nonlinear autoregressive model by minimising the prediction error. The network connectionist weights act as new features and speaker models are created using covariance matrices of acquired features that are compared using Arithmetic-Harmonic Sphericity [130].…”

Section: Discriminative Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Learning Speaker-Specific Characteristics With a Deep Neural Architecture

Chen

Ahmad

2011

IEEE Trans. Neural Netw.

104

View full text Add to dashboard Cite

Speech signals convey various yet mixed information ranging from linguistic to speaker-specific information. However, most of acoustic representations characterize all different kinds of information as whole, which could hinder either a speech or a speaker recognition (SR) system from producing a better performance. In this paper, we propose a novel deep neural architecture (DNA) especially for learning speaker-specific characteristics from mel-frequency cepstral coefficients, an acoustic representation commonly used in both speech recognition and SR, which results in a speaker-specific overcomplete representation. In order to learn intrinsic speaker-specific characteristics, we come up with an objective function consisting of contrastive losses in terms of speaker similarity/dissimilarity and data reconstruction losses used as regularization to normalize the interference of non-speaker-related information. Moreover, we employ a hybrid learning strategy for learning parameters of the deep neural networks: i.e., local yet greedy layerwise unsupervised pretraining for initialization and global supervised learning for the ultimate discriminative goal. With four Linguistic Data Consortium (LDC) benchmarks and two non-English corpora, we demonstrate that our overcomplete representation is robust in characterizing various speakers, no matter whether their utterances have been used in training our DNA, and highly insensitive to text and languages spoken. Extensive comparative studies suggest that our approach yields favorite results in speaker verification and segmentation. Finally, we discuss several issues concerning our proposed approach.

show abstract

Section: Discriminative Featuresmentioning

confidence: 99%

“…The network connectionist weights act as new features and speaker models are created using covariance matrices of acquired features that are compared using Arithmetic-Harmonic Sphericity [130]. The speaker models can also be estimated using GMMs as stated in [105].…”

Section: Discriminative Featuresmentioning

confidence: 99%

Learning Speaker-Specific Characteristics With a Deep Neural Architecture

Chen

Ahmad

2011

IEEE Trans. Neural Netw.

104

View full text Add to dashboard Cite

show abstract

Non-linear Speech Feature Extraction for Phoneme Classification and Speaker Recognition

Chétouani¹,

Faundez-Zanuy²,

Gas³

et al. 2005

Nonlinear Speech Modeling and Applications

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper we propose a new feature extraction algorithm based on non-linear prediction: the Neural Predictive Coding (NPC) model which is an extension of the classical LPC one. We apply this model to two significant tasks: phoneme classification and speaker identification. For the first one, the NPC model is trained with a Minimum Classification Error (MCE) criterion. The experiments carried out with the NTIMIT database show an improvement of the classification rates. For speaker identification, we propose a new feature extraction principle based on the NPC model. We also investigate different initialization methods. The new method gives better performances than the traditional ones (LPC, MFCC and PLP).

show abstract