Search

This work presents a novel framework based on a discriminative auditory feature extractor for speaker recognition over VoIP network. The auditory model that simulates the mid-external and inner ear is incorporated into the conventional Mel Frequency Cepstral Coefficients (MFCC) scheme to produce new parameters that we named Ear Frequency Cepstral Coefficients (EFCCs). The experiments are conducted on the TIMIT corpus and the EFCC, used as input parameters tothe i-vector algorithm. Results showed interesting performances compared to the conventional MFCC parameters. In addition, this improvement was obtained by using fewer parameters (43 EFCCs vs 60 MFCCs) in our experiment.

Mobile environments are highly influenced by ambient noise that can cause a significant deterioration in speech recognition performance. In this study, a new framework integrating a noise-robust frontend (FE) in distributed speech recognition (DSR) is presented. Using the Aurora-2 speech database, the authors evaluate the impact of the proposed multidimensional acoustical analysis on the performance of the Mel-frequency-based European Telecommunications Standards Institute-advanced FE (AFE) combined with the Mel-line spectral frequencies (MLSFs) robust features for highly noisy speech. The stream weights of the resulting multi-stream hidden Markov models are optimised automatically by deploying a novel approach based on a discriminative model combination. Finally, these features are effectively transformed and reduced using the Karhunen–Loeve transform. The proposed MLSF-based FE (MLSF-FE) is shown to exhibit a reduction in the relative error rate. Moreover, the proposed FE provides comparable recognition performance to the current DSR-AFE available in global system of mobile communications.

Publication in the conference proceedings of EUSIPCO, Aalborg, Denmark, 2010

Publication in the conference proceedings of EUSIPCO, Glasgow, Scotland, 2009

Publication in the conference proceedings of EUSIPCO, Lausanne, Switzerland, 2008

The automatic recognition of foreign-accented Arabic speech is a challenging task since it involves a large number of nonnative accents. As well, the nonnative speech data available for training are generally insufficient. Moreover, as compared to other languages, the Arabic language has sparked a relatively small number of research efforts. In this paper, we are concerned with the problem of nonnative speech in a speaker independent, large-vocabulary speech recognition system for modern standard Arabic (MSA). We analyze some major differences at the phonetic level in order to determine which phonemes have a significant part in the recognition performance for both native and nonnative speakers. Special attention is given to specific Arabic phonemes. The performance of an HMM-based Arabic speech recognition system is analyzed with respect to speaker gender and its native origin. The WestPoint modern standard Arabic database from the language data consortium (LDC) and the hidden Markov Model Toolkit (HTK) are used throughout all experiments. Our study shows that the best performance in the overall phoneme recognition is obtained when nonnative speakers are involved in both training and testing phases. This is not the case when a language model and phonetic lattice networks are incorporated in the system. At the phonetic level, the results show that female nonnative speakers perform better than nonnative male speakers, and that emphatic phonemes yield a significant decrease in performance when they are uttered by both male and female nonnative speakers.

Publication in the conference proceedings of EUSIPCO, Toulouse, France, 2002

A method is presented to compensate cepstral coefficients (MFCCs) in a speech recognition system for degraded telephone channel conditions. The technique proposed is based on a combination of the Karhonen–Loeve Transform (KLT) and Genetic Algorithms (GA). The idea consists of projecting the band‐limited MFCCs onto a subspace generated by the genetically optimized KLT principal axes. Experiments show a clear improvement when the method was applied to the NTIMIT speech database. Word recognition results obtained on the HTK toolkit platform using N‐mixture tri‐phone models and a bigram language model are presented and discussed.