Mohammad Mehdi Homayounpour

发表

SpeechOverlap Detection using Spectral Features anditsApplication inSpeech Indexing

M. H. Moattar, Mohammad Mehdi Homayounpour, 2006 .

Performance Improvement of Language Identification Using Transcription Based Sequential Approaches & Sequential Kernels Based SVM

Mohammad Mehdi Homayounpour, Seyed Abbas Hosseini Amereei, 2012 .

Robust feature extraction and uncertainty estimation based on attractor dynamics in cyclic deep denoising autoencoders

Mohammad Mehdi Homayounpour, Amir Hossein Hadjahmadi, M. Homayounpour, 2018, Neural Computing and Applications.

Using Thesaurus to Improve Multiclass Text Classification

Mohammad Mehdi Homayounpour, Nooshin Maghsoodi, 2011, CICLing.

Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy pdf

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2015, Int. J. Pattern Recognit. Artif. Intell..

Uncertainty propagation through neural network bottleneck features

Mohammad Mehdi Homayounpour, Amir Hossein Hadjahmadi, 2015, 2015 23rd Iranian Conference on Electrical Engineering.

Bernoulli versus Markov: Investigation of state transition regime in switching-state acoustic models

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Jahanshah Kabudian, 2009, Signal Process..

Improving Farsi multiclass text classification using a thesaurus and two‐stage feature selection

Mohammad Mehdi Homayounpour, Nooshin Maghsoodi, M. Homayounpour, 2011, J. Assoc. Inf. Sci. Technol..

Consideration of correlation between noise and clean speech signals in autocorrelation-based robust speech recognition

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2007, 2007 9th International Symposium on Signal Processing and Its Applications.

A real-time trained system for robust speaker verification using relative space of anchor models

Mohammad Mehdi Homayounpour, Abbas Samani, Ali Sadeghi-Naini, 2010, Comput. Speech Lang..

Dynamic sparsity control in Deep Belief Networks

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2017, Intell. Data Anal..

Effective sparsity control in deep belief networks using normal regularization term

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, M. Homayounpour, 2017, Knowledge and Information Systems.

Structure Learning in Bayesian Networks Using Asexual Reproduction Optimization

Mohammad Bagher Menhaj, Mohammad Mehdi Homayounpour, Ali Reza Khanteymoori, 2011 .

Text-Independent Speaker Verification Using Variational Gaussian Mixture Model

M. H. Moattar, Mohammad Mehdi Homayounpour, 2011 .

Autocorrelation-based Methods for Noise- Robust Speech Recognition

Mohammad Mehdi Homayounpour, G. Farahani, Mohammad Ahadi, 2007 .

Robust weighted fuzzy c-means clustering

Mohammad Mehdi Homayounpour, Amir Hossein Hadjahmadi, Seyed Mohammad Ahadi, 2008, 2008 IEEE International Conference on Fuzzy Systems (IEEE World Congress on Computational Intelligence).

Machine vs. human speaker verification

Mohammad Mehdi Homayounpour, Jean-Philippe Goldman, 1995 .

Nonparametrically trained PLDA for short duration i-vector speaker verification

Mohammad Mehdi Homayounpour, Abbas Khosravani, 2018, Comput. Speech Lang..

Factorial speech processing models for noise-robust automatic speech recognition

Mohammad Mehdi Homayounpour, Mahdi Khademian, 2015, 2015 23rd Iranian Conference on Electrical Engineering.

DBMiP: A pre-training method for information propagation over deep networks

Mohammad Mehdi Homayounpour, Toktam Zoughi, 2019, Comput. Speech Lang..

Speaker Tracking Using Eigendecomposition and an Index Tree of Reference Models

M. H. Moattar, Mohammad Mehdi Homayounpour, 2011 .

AUT System for SITW Speaker Recognition Challenge

Mohammad Mehdi Homayounpour, Abbas Khosravani, 2016, INTERSPEECH.

Robust feature extraction based on spectral peaks of group delay and autocorrelation function and phase domain analysis

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2006, INTERSPEECH.

Persian TextNormalization UsingClassifi'cation TreeandSupport Vector Machine

M. H. Moattar, Mohammad Mehdi Homayounpour, 2006 .

Normal sparse Deep Belief Network

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, M. Homayounpour, 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

Optimizing spatio-spectral filters by motor imagery pattern quantification in self-paced Brain Computer Interface

Mohammad Mehdi Homayounpour, Hamid Reza HakimDavoodi, 2014, 7'th International Symposium on Telecommunications (IST'2014).

Investigating the effect of phase reconstruction on the bandwidth extention on audio signal using DNNs

Mohammad Mehdi Homayounpour, Mahdieh Ramezani, 2018, 2018 9th International Symposium on Telecommunications (IST).

Improved Autocorrelation-based Noise robust speech recognition using kernel-based cross correlation and overestimation parameters

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2007, 2007 15th European Signal Processing Conference.

Erratum to: Modeling State-Conditional Observation Distribution Using Weighted Stereo Samples for Factorial Speech Processing Models

Mohammad Mehdi Homayounpour, Mahdi Khademian, 2017, Circuits Syst. Signal Process..

A PLDA Approach for Language and Text Independent Speaker Recognition

Gérard Chollet, Mohammad Mehdi Homayounpour, Dijana Petrovska-Delacrétaz, 2016, Odyssey.

A Bayesian Network Based Approach for Data Classification Using Structural Learning

Mohammad Bagher Menhaj, Mohammad Mehdi Homayounpour, Ali Reza Khanteymoori, 2008, CSICC.

Applying continuous action reinforcement learning automata(CARLA) to global training of hidden Markov models

Mohammad Reza Meybodi, Mohammad Mehdi Homayounpour, Jahanshah Kabudian, 2004, International Conference on Information Technology: Coding and Computing, 2004. Proceedings. ITCC 2004..

A Weighted Feature Voting Approach for Robust and Real-Time Voice Activity Detection

M. H. Moattar, Mohammad Mehdi Homayounpour, 2011 .

Gender aware Deep Boltzmann Machines for phone recognition

Mohammad Mehdi Homayounpour, Toktam Zoughi, 2015, 2015 International Joint Conference on Neural Networks (IJCNN).

Speech acts classification of Farsi texts

Mohammad Mehdi Homayounpour, A. Soltani Panah, M. Homayounpour, 2008, 2008 International Symposium on Telecommunications.

Neural Machine Translation on scarce-resource condition: A case-study on Persian-English

Shahram Khadivi, Mohammad Mehdi Homayounpour, Mohaddeseh Bastan, 2017, 2017 Iranian Conference on Electrical Engineering (ICEE).

Improvement on automatic speaker gender identification using classifier fusion

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2010, 2010 18th Iranian Conference on Electrical Engineering.

Use of Spectral Peaks in Autocorrelation and Group Delay Domains for Robust Speech Recognition

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A study of Intra- and Inter-Speaker Variability in the Voices of Twins for Speaker Verification

Gérard Chollet, Mohammad Mehdi Homayounpour, 1995 .

Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models

Mohammad Mehdi Homayounpour, Mahdi Khademian, M. Homayounpour, 2016, Speech Commun..

Adaptive Windows Convolutional Neural Network for Speech Recognition

Mohammad Mehdi Homayounpour, Toktam Zoughi, M. Homayounpour, 2018, Signal and Data Processing.

A PLDA approach for language and text independent speaker recognition

Mohammad Mehdi Homayounpour, Abbas Khosravani, M. Homayounpour, 2016, Comput. Speech Lang..

Performance enhancement for audio-visual speaker identification using dynamic facial muscle model

Farzad Towhidkhah, Mohammad Mehdi Homayounpour, Vahid Asadpour, 2006, Medical and Biological Engineering and Computing.

Feature joint-state posterior estimation in factorial speech processing models using deep neural networks

Mohammad Mehdi Homayounpour, Mahdi Khademian, 2017, Comput. Electr. Eng..

A Gender-Aware Deep Neural Network Structure for Speech Recognition

Mohammad Mehdi Homayounpour, Toktam Zoughi, 2019 .

Persian speech sentence segmentation without speech recognition

Mohammad Mehdi Homayounpour, Hoda Sadat Jafari, 2014, 2014 Iranian Conference on Intelligent Systems (ICIS).

Word Sense Disambiguation of Farsi Homographs Using Thesaurus and Corpus

Mohammad Mehdi Homayounpour, Raheleh Makki, 2008, GoTAL.

Modeling State-Conditional Observation Distribution Using Weighted Stereo Samples for Factorial Speech Processing Models

Mohammad Mehdi Homayounpour, Mahdi Khademian, M. Homayounpour, 2015, Circuits Syst. Signal Process..

Mel sub-band filtering and compression for robust speech recognition

Ahmad Akbari, Mohammad Mehdi Homayounpour, Babak Nasersharif, 2007, INTERSPEECH.

Feature selection and dimension reduction for automatic gender identification

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2009, 2009 14th International CSI Computer Conference.

Features based on filtering and spectral peaks in autocorrelation domain for robust speech recognition

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2007, Comput. Speech Lang..

Adaptive windows multiple deep residual networks for speech recognition

Mohammad Mehdi Homayounpour, Mahmood Deypir, Toktam Zoughi, 2020, Expert Syst. Appl..

Performance improvement in automatic gender identification using hierarchical clustering

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2010, 2010 5th International Symposium on Telecommunications.

Automatic Gender Identification Using Fusion of Generative and Discriminative Classifiers and Clustering of Spekaers from the Same Gender

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, 2012 .

A Persian spoken dialogue system using POMDPs

Mohammad Mehdi Homayounpour, Hesam Mahmoudi, M. Homayounpour, 2015, 2015 The International Symposium on Artificial Intelligence and Signal Processing (AISP).

Linearly Constrained Minimum Variance for Robust I-vector Based Speaker Recognition

Mohammad Mehdi Homayounpour, Abbas Khosravani, 2014, Odyssey.

Robust Feature Extraction of Speech Via Noise Reduction in Autocorrelation Domain

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Gholamreza Farahani, 2006, MRCS.

Time-inhomogeneous hidden Bernoulli model: An alternative to hidden Markov model for automatic speech recognition

Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi, Jahanshah Kabudian, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Tens-embedding: A Tensor-based document embedding method

Mohammad Mehdi Homayounpour, Zahra Rahimi, M. Homayounpour, 2020, Expert Syst. Appl..

Nonparametrically Trained Probabilistic Linear Discriminant Analysis for i-Vector Speaker Verification

Mohammad Mehdi Homayounpour, Abbas Khosravani, 2017, INTERSPEECH.

Spectral peaks enhancement for extracting robust speech features

Ahmad Akbari, Mohammad Mehdi Homayounpour, Babak Nasersharif, 2006, 2006 14th European Signal Processing Conference.

A brief survey on deep belief networks and introducing a new object oriented MATLAB toolbox (DeeBNet) pdf

Mohammad Mehdi Homayounpour, Mohammad Ali Keyvanrad, M. Homayounpour, 2014, ArXiv.

TensSent: a tensor based sentimental word embedding method

Mohammad Mehdi Homayounpour, Zahra Rahimi, M. Homayounpour, 2021, Applied Intelligence.

Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection pdf

Mohammad Mehdi Homayounpour, Ahmad Nickabadi, Amir Mohammad Rostami, 2021, Circuits, systems, and signal processing.

Verification vocale d'identite : dependante et independante du texte

Mohammad Mehdi Homayounpour, 1995 .