The integration of principal component analysis and cepstral mean subtraction in parallel model combination for robust speech recognition

Veisi, Hadi; Sameti, Hossein

doi:10.1016/j.dsp.2010.07.004

Cited by 16 publications

(13 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, a framework is to be designed for the adaptation of the PCA transform matrix in the presence of noise. The PC-PMC method provides solutions to these problems [30].…”

Section: Robustness Methodsmentioning

confidence: 99%

“…In the model-based approach, the models of various sounds used by the classifier are modified to become similar to the test data models. Maximum likelihood linear regression (MLLR) [33,42], maximum a posteriori (MAP) [34,24], parallel model combination (PMC) [23,31,33] and a novel enhanced version of PMC, PCA and CMS based PMC (PC-PMC) [30] are well incorporated in the system. PC-PMC algorithm takes the advantages of additive noise compensation ability of PMC and convolutional noise removal capability of both PCA and CMS methods.…”

Section: Robustness Methodsmentioning

confidence: 99%

“…In the data compensation approach, clean data are estimated from their noisy samples so as to make them similar to the training data. Nevisa uses spectral subtraction (SS) and Wiener filtering [23], cepstral mean subtraction (CMS) [3,23], principal component analysis (PCA) [30] and vocal tract length normalization (VTLN) [27,28,41,29] for this purpose. In the model-based approach, the models of various sounds used by the classifier are modified to become similar to the test data models.…”

Section: Robustness Methodsmentioning

confidence: 99%

“…The modules shown with dotted blocks are robustness modules and can be used optionally. The MFCC module is used as the core of feature extraction unit and is supplied with vocal tract length normalization (VTLN) [27][28][29], cepstral mean subtraction (CMS) [3,23] and principal component analysis (PCA) [30] robustness methods. In addition, voice activity detector (VAD) is used to separate speech segments from non-speech ones.…”

Section: Overviewmentioning

confidence: 99%

See 3 more Smart Citations

A large vocabulary continuous speech recognition system for Persian language

Sameti

Veisi

Bahrani

et al. 2011

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

The first large vocabulary speech recognition system for the Persian language is introduced in this paper. This continuous speech recognition system uses most standard and state-of-the-art speech and language modeling techniques. The development of the system, called Nevisa, has been started in 2003 with a dominant academic theme. This engine incorporates customized established components of traditional continuous speech recognizers and its parameters have been optimized for real applications of the Persian language. For this purpose, we had to identify the computational challenges of the Persian language, especially for text processing and extract statistical and grammatical language models for the Persian language. To achieve this, we had to either generate the necessary speech and text corpora or modify the available primitive corpora available for the Persian language. In the proposed system, acoustic modeling is based on hidden Markov models, and optimized decoding, pruning and language modeling techniques were used in the system. Both statistical and grammatical language models were incorporated in the system. MFCC representation with some modifications was used as the speech signal feature. In addition, a VAD was designed and implemented based on signal energy and zero-crossing rate. Nevisa is equipped with out-of-vocabulary capability for applications with medium or small vocabulary sizes. Powerful robustness techniques were also utilized in the system. Model-based approaches like PMC, MLLR and MAP, along with feature robustness methods such as CMS, PCA, RCC and VTLN, and speech enhancement methods like spectral subtraction and Wiener filtering, along with their modified versions, were diligently implemented and evaluated in the system. A new robustness method called PC-PMC was also proposed and incorporated in the system. To evaluate the performance and optimize the parameters of the system in noisy-environment tasks, four real noisy speech data sets were generated. The final performance of Nevisa in noisy environments is similar to the clean conditions, thanks to the various robustness methods implemented in the system. Overall recognition performance of the system in clean and noisy conditions assures us that the system is a real-world product as well as a competitive ASR engine.

show abstract

“…In addition, a framework is to be designed for the adaptation of the PCA transform matrix in the presence of noise. The PC-PMC method provides solutions to these problems [30].…”

Section: Robustness Methodsmentioning

confidence: 99%

Section: Robustness Methodsmentioning

confidence: 99%

Section: Robustness Methodsmentioning

confidence: 99%

Section: Overviewmentioning

confidence: 99%

See 2 more Smart Citations

A large vocabulary continuous speech recognition system for Persian language

Sameti

Veisi

Bahrani

et al. 2011

J AUDIO SPEECH MUSIC PROC.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Many speaker verification approaches have succeeded in achieving high accuracy in clean conditions but failed in practical applications. This problem occurs partly due to the mismatch between enrollment (labs) and test (real-world) acoustic conditions [1]. Typical solutions to reduce the undesired mismatch can be categorized as feature-based, score-based and model-based compensation.…”

Section: Introductionmentioning

confidence: 99%

A novel speaker verification approach for certain noisy environment

Cao

Jiang

Ying

et al. 2014

2014 12th International Conference on Signal Processing (ICSP)

View full text Add to dashboard Cite

The performance of a speaker verification system is damagingly affected by large amount of noise. In order to compensate the mismatch between enrollment and test acoustic conditions, this paper presents a novel approach based on Gaussian Mixture Model-Universal Background Model (GMM-UBM) algorithm. Noisy background adaption is proposed to make speaker models more close to the one in real-world scenarios. Since there is great difference among various noise types, noise recognition is applied to help choose appropriate background model in accordance with certain noisy condition. Moreover, a Mel-domain de-noise method is used as a suitable noise reduction front-end. Finally, experiments on corrupted TIMIT database showed that the proposal could reduce up to 26.38% and an average of 16.44% equal error rate (EER) compared to the baseline, indicating its advantages on speaker verification under various noisy conditions.

show abstract