Sharif Digital Repository

A comparative study on single-channel noise estimation methods for speech enhancement

Author

Veisi, H.

Pub. Year

2012

Subjects

Minimal tracking. / Comparative performance analysis. / Comparative studies. / Evaluation criteria. / Minimum controlled recursive average. / Noise estimation. / Noise spectrum. / Noise types. / Noisy conditions. / Single-channel. / Speech enhancement system. / VAD. / Intelligent systems. / Signal to noise ratio. / Systems analysis. / Speech enhancement.

Hidden-Markov-model-based voice activity detector with high speech detection rate for speech enhancement

Author

Veisi, H.

Pub. Year

2012

Subjects

Cepstral. / Composite models. / Ergodics. / Noise types. / Noisy speech. / Reference method. / Robust detection. / Soft decision. / Speech detection. / Speech enhancement system. / Speech segments. / Two-state. / Voice activity detection algorithms. / Voice activity detectors. / Detectors. / Hidden Markov models. / Microphones. / Speech analysis. / Speech enhancement. / Speech recognition.

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

Author

Veisi, H.

Pub. Year

2011

Subjects

Automatic speech recognition. / Cepstral mean subtraction (CMS) / Parallel model combination (PMC) / PCA-CMS based PMC (PC-PMC) / Principal component analysis (PCA) / Robustness. / Cepstral mean subtraction. / Parallel model combinations. / Algorithms. / Continuous speech recognition. / Convolution. / Covariance matrix. / Maximum likelihood. / Principal component analysis.

Cepstral-domain HMM-based speech enhancement using vector Taylor series and parallel model combination

Author

Veisi, H.

Pub. Year

2012

Subjects

Accurate estimation. / Auto-regressive. / Cepstral domain. / Evaluation results. / Minimum mean square errors (MMSE) / Noisy speech. / Noisy speech signals. / Parallel model combinations. / Speech enhancement system. / Vector taylor series. / Weighted-sum. / Hidden Markov models. / Information science. / Noise abatement. / Signal processing. / Speech enhancement. / Speech recognition.

A parallel cepstral and spectral modeling for HMM-based speech enhancement

Author

Veisi, H.

Pub. Year

2011

Subjects

Mel-frequency. / parallel cepstral and spectral modeling. / Statistical HMM-based speech enhancement. / Cepstral. / Concurrent modeling. / Distortion effects. / Hidden Markov modeling. / Mel-frequency. / Noise types. / Nonstationary noise. / Spectral domains. / Spectral modeling. / Spectrum estimation. / Speech enhancement system. / Speech spectra. / Digital signal processing. / Frequency domain analysis. / Spectrum analysis. / Speech enhancement. / Frequency estimation.

Speech enhancement using hidden Markov models in Mel-frequency domain

Author

Veisi, H.

Pub. Year

2013

Subjects

HMM-based speech enhancement. / Parallel cepstral and spectral (PCS) / Auto-regressive. / Cepstral. / Clean speech. / Concurrent modeling. / Enhancement framework. / Magnitude spectrum. / Mel-frequency. / Minimum mean square errors. / Noise types. / Noisy signals. / Nonstationary noise. / Reference method. / Spectral domains. / Spectrum estimation. / Spectrum estimators. / Speech enhancement methods. / Frequency domain analysis. / Hidden Markov models. / Signal to noise ratio. / Spectrum analysis. / Speech recognition. / Time series analysis. / Speech enhancement.

An improved parallel model combination method for noisy speech recognition

Author

Veisi, H.

Pub. Year

2009

Subjects

Automatic speech recognition system. / Cepstral mean subtraction. / Continuous speech. / Decorrelations. / Noise removal. / Noisy environment. / Noisy speech recognition. / Novel methods. / Parallel model combinations. / Persians. / Word error rate. / Continuous speech recognition. / Solenoids. / Principal component analysis.

A complexity-based approach in image compression using neural networks

Author

Veisi, H.

Pub. Year

2009

Subjects

Adaptive image compression. / JPEG standard. / Multi-layer perceptron neural network. / Adaptive approach. / Adaptive methods. / Back propagation artificial neural network (BPANN) / Complexity estimation. / Complexity levels. / Complexity measures. / Image blocks. / Image complexity. / Input image. / JPEG standards. / Multi layer perceptron. / Multi-layer perceptron neural networks. / Network-based. / PSNR. / Image compression. / Neural networks. / Compressors.

Investigation of the equivalent material properties and failure stress of the re-entrant composite lattice structures using an analytical model

Author

Veisi, H.

Publisher

Elsevier Ltd,

Pub. Year

2020

Subjects

Equivalent mechanical properties. / Failure stress. / Re-entrant honeycomb. / Theoretical modeling. / Analytical models. / Biomechanics. / Buckling. / Cells. / Composite structures. / Cytology. / Density (specific gravity) / Fiber reinforced plastics. / Honeycomb structures. / Laminated composites. / Lattice theory. / Struts. / Classical laminate theory. / Composite laminate. / Composite lattices. / Equivalent material properties. / Failure properties. / Lattice structures. / Mechanical constants. / Structural properties.

Improving the performance of speech recognition systems using fault-tolerant techniques

Author

Veisi, H.

Pub. Year

2008

Subjects

Fault tolerant technique. / Fault-tolerant. / Persian speech. / Plurality voting. / Recognition methods. / Speech recognition systems. / Fault tolerant computer systems. / Nuclear magnetic resonance spectroscopy. / Signal processing. / Speech analysis. / Speech recognition.

Noise and speaker robustness in a persian continuous speech recognition system

Author

Veisi, H.

Pub. Year

2007

Subjects

Computer networks. / Continuous speech recognition. / Signal processing. / Speech. / Speech analysis. / Weaving. / International symposium. / Persian. / Warping factors. / Speech recognition.

Image compression with neural networks using complexity level of images

Author

Veisi, H.

Pub. Year

2007

Subjects

Acoustic intensity. / Backpropagation. / Compressors. / Digital image storage. / Image coding. / Image compression. / Metropolitan area networks. / Programming theory. / Signal processing. / Signal to noise ratio. / Vegetation. / Complexity levels. / Complexity measures. / Image blocks. / Image complexity. / Image compression methods. / Input images. / JPEG. / JPEG standards. / Multi-layer perceptron. / PSNR. / Trained networks. / Neural networks.

The combination of CMS with PMC for improving robustness of speech recognition systems

Author

Veisi, H.

Pub. Year

2008

Subjects

Acoustic adaptation. / Automatic speech recognition system. / Cepstral mean subtraction. / Parallel model combinations. / Real applications. / Recognition systems. / Robustness. / Speaker normalization. / Speech recognition systems. / Computer science. / Convolution. / Speech recognition.

An optimum MMSE post-filter for Adaptive Noise Cancellation in automobile environment

Author

Khorram, S.

Pub. Year

2012

Subjects

Adaptive noise cancellations. / Background noise reduction. / Dual channel. / Filter coefficients. / Linear filters. / MMSE estimation. / Noise spectra. / Noisy environment. / Nonstationary. / Postfilters. / Speech distortion. / Speech signals. / Uncorrelated noise. / Vehicular environments. / Voice activity detectors. / Information science. / Signal denoising. / Spectrum analysis. / Speech enhancement. / Spurious signal noise.

An algebraic gain estimation method to improve the performance of HMM-based speech enhancement systems

Author

Mariooryad, S.

Pub. Year

2010

Subjects

Hidden Markov model. / Algebraic gain estimation. / Gain estimation. / Least square errors. / Minimum mean square error. / Minimum mean square errors. / Block codes. / Electrical engineering. / Estimation. / Hidden Markov models. / Least squares approximations. / Mean square error. / Speech enhancement. / Algebra. / Least square error.

LP-based over-sampled subband adaptive noise canceller for speech enhancement in diffuse noise fields

Author

Khorram, S.

Pub. Year

2008

Subjects

Adaptive noise canceller. / Analysis and synthesis. / Diffuse noise. / Hybrid structure. / Linear prediction. / Noise reductions. / Postfilter. / Prototype filters. / Quality measures. / Speech enhancement system. / Sub-band. / Signal processing. / Speech enhancement. / Spurious signal noise. / Microphones.