A noise-robust front-end for distributed speech recognition in mobile communications

Addou, Djamel; Selouani, Sid‐Ahmed; Kifaya, Kaoukeb; Boudraa, Malika; Boudraa, Bachir

doi:10.1007/s10772-009-9025-9

Cited by 9 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to improve the noise robustness of the DSR front-end; one must combine the MFCCs with features that are robust against noise. PLP features [4], RASTA features [5], and spectral peaks, also known as formant-like features [1], are some of the features that are known to be robust against additive noise. Choosing the best feature set highly depends on the application and constraints.…”

Section: Overview Of Distributed Speech Recognitionmentioning

confidence: 99%

“…In previous work [1,13], we introduced a multi-stream paradigm for DSR in which, we merge different sources of information about the speech signal that could be lost when using only the MFCCs to recognize uttered speech. Our experiments showed that such multi-variable, integrating some parameters based on a model simulating the cochlea and the acoustic cues reflecting the spectral resonances (formants), leads to an improved recognition rate.…”

Section: Introductionmentioning

confidence: 99%

“…The obtained results showed that the use of the formant frequencies for ASR in a multi-stream paradigm improves the ASR performance. Then in [1], we extended our work to evaluate the robustness of the above mentioned proposed features using a multi-stream paradigm for ASR in distributed environments. In this latter configuration the weights of each stream is determined empirically and remain constant after being fixed.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An Efficient Front-End for Distributed Speech Recognition over Mobile

Addou¹,

Ahmed²,

Boudraa³

et al. 2012

IJCCE

Self Cite

View full text Add to dashboard Cite

To improve the robustness of distributed speech front-ends in mobile communication we introduce, in this paper, a new set of feature vector which is estimated through three steps. First, the Mel-Line Spectral Frequencies (MLSFs) coefficients are combined with conventional MFCCs, after extracted from a denoised acoustic frame using the wiener filter. Also, we optimize the stream weights of multi-stream HMMs by deploying a discriminative approach. Finally, these features are adequately transformed and reduced in a multi-stream scheme using Karhunen-Loeve Transform (KLT). Recognition experiments on the Aurora 2 connected digits database reveal that the proposed front-end leads to a significant improvement in speech recognition accuracy for highly noisy GSM.

show abstract

Section: Overview Of Distributed Speech Recognitionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

An Efficient Front-End for Distributed Speech Recognition over Mobile

Addou¹,

Ahmed²,

Boudraa³

et al. 2012

IJCCE

Self Cite

View full text Add to dashboard Cite

show abstract

“…In our previous work [14, 15], we investigated the potential of a multi‐stream FE using the formant frequencies and line spectral frequencies (LSFs) features combined with conventional MFCCs to improve the performance of a DSR basic (FE) system in severely degraded environments. Formant and LSF features are more suitable for our application because extracting them can be done as part of the mel‐frequency cepstral coefficients (MFCC) extraction process, saving a lot of computation.…”

Section: Introductionmentioning

confidence: 99%

Optimisation of multiple feature stream weights for distributed speech processing in mobile environments

Addou

Selouani

2015

IET signal process.

View full text Add to dashboard Cite

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-Loève 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.

show abstract

“…The latter is then used to train multi-stream hidden Markov models (HMMs). The reason that motivated us to consider LSFs is related to the fact that LSF regions of the spectrum may stay above the noise level even in very low SNR ratio, while the lower energy regions will tend to be masked by the noise energy [8]. Moreover, the extraction LSF parameters can be done as part of the process of MFCCs calculation which allows reducing significantly the added computation load.…”

Section: Introductionmentioning

confidence: 99%

A Front-End Processing Using Subspace-Based Speech Enhancement over Mobile Devices

Daalache¹,

Addou²,

Boudraa³

2014

JACN

View full text Add to dashboard Cite

Abstract-The paradigm multi-stream has been shown to result in features combined that can help to increase the robustness of distributed speech recognition (DSR) in the mobile communications. In this paper, we employs a combination of post proceeded Mel-cepstral coefficients (MFCCs) and line spectral frequencies features (LSFs) projected in linear discriminate analysis (LDA) space. The experiments performed on the Aurora 2.0 database using multi-condition training set show that, even with fewer parameters, the proposed front-end provides comparable recognition results to the standard ETSI WI008 advanced front-end, nowadays available in the vocal commands of the GSM mobile communications, while achieving higher accuracy when the signal-to-noise ratio (SNR) is very low.Index Terms-Distributed speech recognition, linear discriminate analysis, multi-stream hidden Markov models, Mel-cepstral coefficients, line spectral frequencies.

show abstract

A noise-robust front-end for distributed speech recognition in mobile communications

Cited by 9 publications

References 8 publications

An Efficient Front-End for Distributed Speech Recognition over Mobile

An Efficient Front-End for Distributed Speech Recognition over Mobile

Optimisation of multiple feature stream weights for distributed speech processing in mobile environments

A Front-End Processing Using Subspace-Based Speech Enhancement over Mobile Devices

Contact Info

Product

Resources

About