Hossein Sameti.jpg

 

Hossein Sameti
Associate Professor

Department of Computer Engineering
Sharif University of Technology

  Tel

+98 21 66166637

  Fax

+98 21 66019246

  Mailing address

Room 706, Department of Computer Engineering, Sharif University of Technology, Azadi Avenue, Tehran 14588, Iran

  E-Mail

sameti [at] sharif [dot] edu

 

About Our Group

Education

Research Interests

 Publications

Courses

Students

Speech Processing Lab

AI GROUP ANNOUNCEMENTS

 

 :: About Our Group

 

 

Director of the speech processing research group, Sharif University of Technology

This research group started to work in 1999 and it has about 32 researchers presently. Our major projects are as follows:

1)   A Persian (Farsi) large vocabulary continuous speech recognition engine which can be utilized in different speech recognition products. The project includes research in different areas of automatic speech recognition and incorporation of different known methods for the Persian language. The system is a large vocabulary speaker-independent continuous speech recognition (LVCSR) system based on hidden Markov models (HMM). The vocabulary of the ASR system consists of more than 65,000 most common words of the Persian language.

2)   Spoken dialogue systems for the Persian language. We are developing the first speech enabled IVR system and dialogue systems in Persian. The system is developed for banking and ticketing applications and is launched for evaluation.

3)   Persian text to speech engine. This engine provides the most natural speech in Persian and includes very sophisticated text to phoneme transformer. It can handle complexities of Persian text such as kasre-ezafe and numerous homographs.

4)   Speaker identification over phone line.

5)   Keyword spotting

For more information about the group visit our lab website spl.ce.sharif.edu. Also the company web site, www.asr-gooyesh.com contains more detailed information about our speech products.

 

 

 

p

 :: Education

 

 

 

 

 

p

 :: Research Interests

 

 

  • Speech Processing
  • Spoken Dialogue Systems
  • Natural Language Understanding
  • Automatic Speech Recognition
  • Natural Language Modeling
  • Hidden Markov Modeling of Speech
  • Speech Enhancement

 :: Publications

 

 

Journal Papers

 

[1]      M. Mortaza Taheri-Ardali, M. Aasi, H. Sameti, and M. Bijankhan, “Prosodic Focus Modeling in Persian: An Articulatory–Functional Approach,” Comparative Linguistic Researches, vol. 5, no. 10, pp. 37-56 (in Persian), 2016.

[2]      E. Golrasan, and H. Sameti, “Speech enhancement based on hidden Markov model using sparse code shrinkage,” Journal of AI and Data Mining, vol. 4, no. 2, pp. 213-218, 2016.

[3]      M. H. Bokaei, H. Sameti, and Y. Liu, “Summarizing Meeting Transcripts Based on Functional Segmentation,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 24, no. 10, pp. 1831-1841, 2016.

[4]      M. H. Bokaei, H. Sameti, and Y. Liu, “Extractive summarization of multi-party meetings through discourse segmentation,” Natural Language Engineering, vol. 22, no. 01, pp. 41-72, 2016.

[5]      H. Zeinali, A. Mirian, H. Sameti, and B. BabaAli, “Non-speaker information reduction from Cosine Similarity Scoring in i-vector based speaker verification,” Computers & Electrical Engineering, vol. 48, pp. 226-238, 2015.

[6]      S. Khorram, H. Sameti, and S. King, “Soft context clustering for F0 modeling in HMM-based speech synthesis,” EURASIP Journal on Advances in Signal Processing, vol. 2015, no. 1, pp. 1-17, 2015.

[7]      S. Khorram, H. Sameti, and F. Bahmaninezhad, “Spectral Modeling Based on GAUSSIAN Conditional Random Field for Statistical Parametric Speech Synthesis,” CSI Journal on Computer Science and Engineering, vol. 13, 2015.

[8]      M. H. Bokaei, H. Sameti, and Y. Liu, “Linear discourse segmentation of multi-party meetings based on local and global information,” Audio, Speech, and Language Processing, IEEE/ACM Transactions on, vol. 23, no. 11, pp. 1879-1891, 2015.

[9]      A. Aroudi, H. Veisi, H. Sameti, and Z. Mafakheri, “Speech signal modeling using multivariate distributions,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2015, no. 1, pp. 1-14, 2015.

[10]    A. Aroudi, H. Veisi, and H. Sameti, “Hidden Markov model-based speech enhancement using multivariate Laplace and Gaussian distributions,” Signal Processing, IET, vol. 9, no. 2, pp. 177-185, 2015.

[11]    S. Khorram, H. Sameti, F. Bahmaninezhad, S. King, and T. Drugman, “Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2014, no. 1, pp. 1-21, 2014.

[12]    M. Karami, P. Jamshidlou, and H. Sameti, “Emotion Detection for Persian Speakers Using Acoustic Features,” Journal of Acoustics and Vibration, vol. 2, no. 4, pp. 3-13 (in Persian), 2014.

[13]    H. Veisi, and H. Sameti, “Speech enhancement using hidden Markov models in Mel-frequency domain,” Speech Communication, vol. 55, no. 2, pp. 205-220, 2013.

[14]    H. Veisi, and H. Sameti, “Hidden-Markov-model-based voice activity detector with high speech detection rate for speech enhancement,” IET Signal Processing, vol. 6, no. 1, pp. 54-63, February, 2012.

[15]    N. Najkar, F. Razzazi, and H. Sameti, “An evolutionary decoding method for HMM-based continuous speech recognition systems using particle swarm optimization,” Pattern Analysis and Applications, pp. 1-13, 2012.

[16]    B. Abdolai, and H. Sameti, “A Novel Method for Speech Segmentation Based on Speakers' Characteristics,” Signal & Image Processing : An International Journal (SIPIJ), vol. 3, no. 2, pp. 65-78, 2012.

[17]    H. Veisi, and H. Sameti, “The integration of principal component analysis and cepstral mean subtraction in parallel model combination for robust speech recognition,” Digital Signal Processing, vol. 21, no. 1, pp. 36-53, 2011.

[18]    H. Sameti, H. Veisi, M. Bahrani, B. Babaali, and K. Hosseinzadeh, “A Large Vocabulary Continuous Speech Recognition System for Persian Language,” EURASIP Journal on Audio, Speech, and Music Processing, vol. 2011, no. 6, pp. 1-12, 2011.

[19]    M. Bahrani, H. Sameti, and M. Hafezi, “A Computational Grammar for Persian Based on GPSG,” Language Resources and Evaluation, Springer, vol. 45, no. 4, pp. 387-408, 2011.

[20]    M. Bahrani, and H. Sameti, “Building statistical language models for persian continuous speech recognition systems using the peykare corpus,” International Journal of Computer Processing Of Languages, vol. 23, no. 01, pp. 1-20, 2011.

[21]    B. BabaAli, H. Sameti, and T. H. Falk, “A model distance maximizing framework for speech recognizer-based speech enhancement,” AEU - International Journal of Electronics and Communications, Elsevier, vol. 65, pp. 99-106, 2011.

[22]    N. Najkar, F. Razzazi, and H. Sameti, “A novel approach to HMM-based speech recognition systems using particle swarm optimization,” Mathematical and Computer Modelling, Elsevier, vol. 52, pp. 1910-1920, 2010.

[23]    M. Habibi, H. Sameti, and H. Setareh, “On-Line Learning of a Persian Spoken Dialogue System Using Real Training Data,” Journal of Advances in Computer Research, vol. 1, no. 2, pp. 31-39, 2010.

[24]    M. Bahrani, and H. Sameti, “A New Bigram-PLSA Language Model for Speech Recognition,” EURASIP Journal on Advances in Signal Processing, Hindawi, vol. 2010, pp. 1-8, 2010.

[25]    B. Babaali, H. Sameti, and M. Safayani, “Likelihood Maximizing Based Multi-Band Spectral Subtraction for Robust Speech Recognition,” EURASIP Journal on Advances in Signal Processing, Hindawi, vol. 2009, pp. 1-15, 2009.

[26]    S. Shirali-Shahreza, H. Sameti, and M. Shirali-Shahreza, “Parental control based on speaker class verification,” IEEE Transactions on Consumer Electronics, vol. 54, no. 3, pp. 1244-1251, 2008.

[27]    M. Bahrani, and H. Sameti, “Extraction and Modeling Context-Dependent Phone Units for Improvement of Continuous Speech Recognition Accuracy by Phoneme Clustering,” Iranian Journal of Electrical and Computer Engineering, vol. 3, no. 1, pp. 45-51 (In Persian), 2004.

[28]    H. Sameti, and L. Deng, “Nonstationary-state hidden Markov model representation of speech signals for speech enhancement,” Signal Processing, Elsevier, vol. 82, no. 2, pp. 205-227, 2002.

[29]    H. Sameti, H. Sheikhzadeh, L. Deng, and R. L. Brennan, “HMM-Based Strategies for Enhancement of Speech Signals Embedded in Nonstationary Noise,” IEEE Transactions on Speech and Audio Processing vol. 6, no. 5, pp. 445-455, 1998.

[30]    L. Deng, and H. Sameti, “Transitional speech units and their representation by regressive Markov states: applications to speech recognition,” IEEE Transactions on Speech and Audio Processing, vol. 4, no. 4, pp. 301-306, 1996.

[31]    L. Deng, and H. Sameti, “Articulatory phonology and speech recognition: A case study involving use of dynamically defined speech primitives,” The Journal of the Acoustical Society of America, vol. 95, pp. 2870, 1994.

 

                                               

Conference Papers:

 

[1]      H. Zeinali, H. Sameti, L. Burget, J. Černocký, N. Maghsoodi, and P. Matějka, "i-vector/HMM Based Text-dependent Speaker Verification System for RedDots Challenge," Interspeech 2016, pp. 440-444, 2016.

[2]      H. Zeinali, L. Burget, H. Sameti, O. Glembek, and O. Plchot, "Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker Verification," in Odyssey 2016, Bilbao, Spain, 2016.

[3]      N. Maghsoodi, H. Sameti, and H. Zeinali, "Localized discriminative Gaussian process latent variable model for text-dependent speaker verification," in ESANN 2016, 2016, pp. 1-6.

[4]      H. Zeinali, H. Sameti, and H. Hadian, "Real-Time Speaker Identification Using Speaker Model Distance," in 23rd Iranian Conference on Electrical Engineering (ICEE2015), Tehran, Iran, 2015, pp. 1-5.

[5]      H. Zeinali, E. Kalantari, H. Sameti, and H. Hadian, "Telephony text-prompted speaker verification using i-vector representation," in Acoustics, Speech and Signal Processing (ICASSP), 2015 IEEE International Conference on, 2015, pp. 4839-4843.

[6]      E. Kalantari, H. Sameti, and H. Zeinali, "Speaker models reduction for optimized telephony text-prompted speaker verification," in Electrical and Computer Engineering (CCECE), 2015 IEEE 28th Canadian Conference on, 2015, pp. 1470-1474.

[7]      E. Kalantari and H. Sameti, "Generating an Independent Model for Each Speaker in Text-Prompted Speaker Verification Using Limited Enrollment Data," in 23rd Iranian Conference on Electrical Engineering (ICEE2015), Tehran, Iran, 2015, pp. 1-6 (in Persian).

[8]      M. H. Bokaei, H. Sameti, and Y. Liu, "Extractive Meeting Summarization Through Speaker Zone Detection," in Sixteenth Annual Conference of the International Speech Communication Association (Interspeech 2015), 2015, pp. 1-5.

[9]      M. H. Bokaei, H. Sameti, and Y. Liu, "Unsupervised approach to extract summary keywords in meeting domain," in Signal Processing Conference (EUSIPCO), 2015 23rd European, 2015, pp. 1406-1410.

[10]    S. Pouyanfar and H. Sameti, "Music emotion recognition using two level classification," in Intelligent Systems (ICIS), 2014 Iranian Conference on, 2014, pp. 1-6.

[11]    S. Khorram, H. Sameti, and F. Bahmaninezhad, "Context-dependent deterministic plus stochastic model," in Signal Processing (ICSP), 2014 12th International Conference on, 2014, pp. 561-566.

[12]    S. Khorram, H. Sameti, and F. Bahmaninezhad, "Spectral Modeling Based On Hidden Markov Random Field For Statistical Parametric Speech Synthesis," presented at the 2014 IEEE Machine Learning for Signal Processing Workshop, Reims, France, 2014.

[13]    M. R. Hasanabadi and H. Sameti, "Considerations for Generating a Spontaneous Persian Database," in 3rd Conference on Computational Linguistics, Tehran, Iran, 2014, pp. 1-13.

[14]    H. Hadian and H. Sameti, "Active Learning in Noisy Conditions for Spoken Language Understanding," in COLING, 2014, pp. 1081-1090.

[15]    H. Zeinali, H. Sameti, and H. Veisi, "Design and Collection of Persian Telephony Corpus for Text-Dependent Speaker Verification," presented at the Iranian Conference on Electrical Engineering (ICEE), Mashhad, Iran, 2013.

[16]    F. S. Saleh, B. Shams, H. Sameti, and S. Khorram, "An Automatic Prosodic Event Detector Using MSD HMMs for Persian Language," in Artificial Intelligence and Signal Processing, ed: Springer, 2013, pp. 234-240.

[17]    S. Khorram, F. Bahmaninezhad, and H. Sameti, "Speech Synthesis Based on Gaussian Conditional Random Fields," in Artificial Intelligence and Signal Processing, ed: Springer, 2013, pp. 183-193.

[18]    P. Jamshidlou, M. Karami, and H. Sameti, "Emotion Detection in Persian Speech Using Acoustic Features," in International Symposium on Acoustics and Vibration, Tehran, Iran, 2013, pp. 1-8 (in Persian).

[19]    F. Bahmaninezhad, S. Khorram, and H. Sameti, "Average Voice Modeling Based on Unbiased Decision Trees," in Advances in Nonlinear Speech Processing, ed: Springer, 2013, pp. 89-96.

[20]    M. Aminian, M. S. Rasooli, and H. Sameti, "Unsupervised Induction of Persian Semantic Verb Classes Based on Syntactic Information," in IIS, Warsaw, Polad, 2013, pp. 112-124.

[21]    H. Zeinali, H. Sameti, H. Khaki, and B. Babaali, "A fast two-level Speaker Identification method employing sparse representation and GMM-based methods," in Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on, Montreal, Canada, 2012, pp. 80-83.

[22]    H. Zeinali, H. Sameti, and B. Babaali, "A fast Speaker Identification method using nearest neighbor distance," in Signal Processing (ICSP), 2012 IEEE 11th International Conference on, Beijing, China, 2012, pp. 2159-2162.

[23]    H. Veisi and H. Sameti, "A comparative study on single-channel noise estimation methods for speech enhancement," in Intelligent Systems Design and Applications (ISDA), 2012 12th International Conference on, 2012, pp. 645-650.

[24]    H. Veisi and H. Sameti, "The effect of phase information in speech enhancement and speech recognition," in Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on, Montreal, Canada, 2012, pp. 334-339.

[25]    S. H. Mohammadi, H. Sameti, M. S. E. Langarani, and A. Tavanaei, "KNNDIST: A Non-Parametric Distance Measure for Speaker Segmentation," in INTERSPEECH, 2012, pp. 2282-2285.

[26]    S. Khorram, H. Sameti, and H. Veisi, "An optimum MMSE post-filter for Adaptive Noise Cancellation in automobile environment," in Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on, Montreal, Canada, 2012, pp. 455-459.

[27]    S. Khorram, H. Sameti, and S. Bahaaddini, "Model Sampling for Statistical Parametric Speech Synthesis " presented at the 2012 IEEE International Workshop on Multimedia Signal Processing, 2012.

[28]    M. Elyasi, H. Veisi, and H. Sameti, "The effect of phase information in speech enhancement and speech recognition " in Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on, Montreal, Canada, 2012, pp. 1487-1488.

[29]    F. Bahmaninezhad, H. Sameti, and S. Khorram, "HMM-based persian speech synthesis using limited adaptation data," in Signal Processing (ICSP), 2012 IEEE 11th International Conference on, Beijing, China, 2012, pp. 585-589.

[30]    S. Bahaaddini, H. Sameti, F. Jabbari, and S. H. R. Mohammadi, "Glottal Pulse Shape Optimization using Simulated Annealing," in International Symposium on Artificial Intelligence and Signal Processing (AISP 2012), Shiraz, Iran, 2012.

[31]    A. Aroudi, H. Sameti, and H. Veisi, "Speech enhancement based on hidden Markov model with discrete cosine transform coefficients using Laplace and Gaussian distributions," in Information Science, Signal Processing and their Applications (ISSPA), 2012 11th International Conference on, Montreal, Canada, 2012, pp. 340-345.

[32]    H. Veisi and H. Sameti, "A Parallel Cepstral and Spectral Modeling for HMM-Based Speech Enhancement," presented at the 17th International Conference on Digital Signal Processing, DSP2011, Corfu, Greece, 2011.

[33]    A. H. Tavanaei and H. Sameti, "False Alarm Reduction By Improved Filler Model And Post-Processing In Speech Keyword Spotting," in 2011 IEEE International Workshop on Machine Learning for Signal Processing, Beijing, China, 2011.

[34]    A. H. Tavanaei, M. T. Manzoori, and H. Sameti, "Mel-Scaled Discrete Wavelet Transform and Dynamic Features for the Persian Phoneme " in International Symposium on Artificial Intelligence and Signal Processing (AISP 2011), Tehran, Iran, 2011.

[35]    E. Sakhaee, H. Sameti, and B. Babaali, "Incorporating a novel confidence scoring method in a Persian spoken dialogue system," presented at the Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2011, Poznan, Poland, 2011.

[36]    S. H. R. Mohammadi, H. Sameti, A. H. Tavanaei, and A. Soltani Farani, "Filter-bank Design Based on Dependencies Between Frequency Components and Phoneme Characteristics," in 19th European Signal Processing Conference (EUSIPCO2011), Barcelona, Spain, 2011.

[37]    F. Jabbari, H. Sameti, and M. H. Bokaei, "Persian Language Understanding Using a Two-Step Extended Hidden Vector State Parser," in 2011 IEEE International Workshop on Machine Learning for Signal Processing, Beijing, China, 2011.

[38]    H. Eghbalzadeh, F. Sobhan-Manesh, H. Sameti, and B. Babaali, "Speaker phone mode classification using Gaussian mixture models," presented at the Signal Processing Algorithms, Architectures, Arrangements, and Applications Conference Proceedings (SPA), 2011, Poznan, Poland, 2011.

[39]    S. Bahaaddini, H. Sameti, and S. H. R. Mohammadi, "Comparative Study Of Different Excitation Signals On Mel-generalized " in International Symposium on Artificial Intelligence and Signal Processing (AISP 2011), Tehran, Iran, 2011.

[40]    S. Bahaaddini, H. Sameti, and S. khorram, "Implementation And Evaluation Of Statistical Parametric Speech Synthesis Methods For The Persian Language," in 2011 IEEE International Workshop on Machine Learning for Signal Processing, Beijing, China, 2011.

[41]    B. Babaali, H. Sameti, A. Rahmanian, and N. Hassanlou, "A New Probability Density Modeling for HMM-based Speech Recognition," in 3rd International Conference on Signal Acquisition and Processing (ICSAP 2011), Singapore, 2011.

[42]    S. Maryooriad, H. Sameti, and H. Veisi, "An Algebraic Gain Estimation Method to Improve the Performance of HMM-Based Speech Enhancement Systems," in 18th Iranian Conference on Electrical Engineering, Isfahan, 2010.

[43]    M. Habibi, H. Sameti, and H. Setareh, "On-Line Learning of a Persian Spoken Dialogue System Using Real Training Data," in ISSPA2010 International Conference on Information Sciences, Signal Processing and their Applications, Kuala Lumpur, Malaysia, 2010, pp. 133-136.

[44]    M. Habibi, S. Rahbar, and H. Sameti, "Divided POMDP Method for Complex Menu Problems in Spoken Dialogue Systems," in IEEE Workshop on Spoken Language Technology, SLT 2010, Berkley, California, USA, 2010.

[45]    S. Dabbaghchian, H. Sameti, and M. Ghaemmaghmi, "Robust Phoneme Recognition Using MLP Neural Networks in Various Domains of MFCC features " in 5th International Symposium on Telecommunications (IST2010), Tehran, 2010.

[46]    M. H. Bokaei, H. Sameti, H. Eghbalzadeh, B. Babaali, K. Hosseinzadeh, M. Bahrani, et al., "Niusha, the first Persian speech-enabled IVR platform," in 5th International Symposium on Telecommunications (IST2010), Tehran, 2010.

[47]    M. H. Bokaei, H. Sameti, M. Bahrani, and B. Babaali, "Segmental HMM-Based part-of-speech tagger," in 2010 International Conference on Audio, Language and Image Processing, Shanghai, China, 2010.

[48]    S. Bakhshaei, S. Khadivi, H. Riahi, and H. Sameti, "Statistical Machine Translation Parameters on Farsi-English System," in 5th International Symposium on Telecommunications (IST2010), Tehran, 2010.

[49]    H. Veisi and H. sameti, "An Improved Parallel Model Combination Method for Noisy Speech Recognition," in The eleventh biannual IEEE workshop on Automatic Speech Recognition and Understanding (ASRU 2009), Merano, Italy, 2009, pp. 237-242.

[50]    S. Shirali-Shahreza, H. abolhassani, H. Sameti, and M. Shirali-Shahreza, "Spoken CAPTCHA: A CAPTCHA System for Blind Users," in 2009 ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM2009, 8-9 August, Sanya, China, 2009, pp. 1-4.

[51]    N. Najkar and H. Sameti, "A Novel Approach to HMM-Based Speech Recognition System Using Particle Swarm Optimization " in The Fourth International Conference on Bio-Inspired Computing: Theories and Applications, BIC-TA 2009, Beijing, China, 2009, pp. 296-301.

[52]    S. Momtazi and H. Sameti, "A Possibilistic Approach for Building Statistical Language Models," in Ninth International Conference on Intelligent Systems Design and Applications (ISDA09), Pisa, Italy, 2009, pp. 1014-1018.

[53]    F. Khalili, M. Ardebilipour, and H. Sameti, "Design and implementation of vector quantizer for a 600 bps vocoder based on MELP," in Proceedings of the 11th international conference on Advanced Communication Technology (ICACT 2009) - Volume 2, Gangwon-Do, South Korea, 2009, pp. 1487-1490.

[54]    F. Kaveh, H. Sameti, and M. Bahrani, "Combining Language Models for Persian Speech Understanding in a Dialogue System," in 14th Annual Computer Society of Iran Computer Conference (CSICC09), Tehran, Iran, 2009.

[55]    P. Habashi and H. Sameti, "Unit Selection Method for Persian Speech Synthesis Using Fastvox," in 14th Annual Computer Society of Iran Computer Conference (CSICC09), Tehran, Iran, 2009.

[56]    M. Ghaemmaghmi, H. Sameti, F. Razzazi, S. Dabbaghchian, and B. Babaali, "Robust Speech Recognition Using MLP Neural Network in Log-Spectral Domain," in IEEE International Symposium on Signal Processing and Information Technology (ISSPIT2009), Ajman, UAE, 2009.

[57]    M. Ghaemmaghmi, H. Sameti, F. Razzazi, S. Dabbaghchian, and B. Babaali, "Noise Reduction Algorithm for Robust Speech Recognition Using MLP Neural Network," in 2009 Asia-Pacific Conference on Computational Intelligence and Industrial Applications (PACIIA 2009), Wuhan, China, 2009.

[58]    H. Veisi and H. Sameti, "The Combination of CMS with PMC for Improving the Robustness of Speech Recognition Systems," in Advances in Computer Science and Engineering, CCIS 6, Springer Berlin Heidelberg, Proceedings of 13th International CSI Computer Conference, CSICC 2008, Kish Island, Iran, March 9-11, Revised Selected Papers, 2008, pp. 825-829.

[59]    H. Veisi and H. Sameti, "Improving the performance of speech recognition systems using fault-tolerant techniques," in 9th International Conference on Signal Processing, ICSP'08, 26-29 October, Beijing, China, 2008, pp. 579-582.

[60]    M. Soufifar, H. Sameti, B. Babaali, and K. Hosseinzadeh, "Introducing a method for using monogram and trigram combinational predictive language model in large vocabulary continuous speech recognition," in 13th International CSI Computer Conference, CSICC 2008, March 9-11, Kish Island, Iran, 2008, p. (In Persian).

[61]    H. Sameti, H. Veisi, M. Bahrani, B. Babaali, and K. Hosseinzadeh, "Nevisa, a Persian Continuous Speech Recognition System," in Advances in Computer Science and Engineering,  CCIS 6, Springer Berlin Heidelberg, Proceedings of 13th International CSI Computer Conference, CSICC 2008 Kish Island, Iran, March 9-11, 2008 Revised Selected Papers 2008, pp. 485-492.

[62]    H. Sajedi, H. Sameti, and H. Beigi, "MPSO: An algorithm for finding global optimum in complex problems," in 13th International CSI Computer Conference, CSICC 2008, March 9-11, Kish Island, Iran, 2008, p. (In Persian).

[63]    Y. Poorebrahim, H. Sameti, and H. Zakipoor, "Implementation of a 1200 bps vocoder based on MELP " in 16th Iranian Conference on Electrical Engineering, Tehran, Iran, 2008, pp. 396-401 (In Persian).

[64]    N. Nasiri, H. Sameti, M. Bahrani, and B. Babaali, "Triphone modeling in HMM-based Persian continuous speech recognition systems," in 13th International CSI Computer Conference, CSICC 2008,  March 9-11, Kish Island, Iran, 2008, p. (In Persian).

[65]    S. Khorram, H. Sameti, H. Veisi, and H. R. Abutalebi, "A New Lattice LP-Based Post-Filter for Adaptive Noise Cancellers in Mobile and Vehicular Applications," in The 8th IEEE Symposium on Signal Processing and Information Technology, ISSPIT 2008, 16-19 December, Sarajevo, Bosnia & Herzegovina, 2008, pp. 407-412.

[66]    S. Khorram, H. Sameti, and H. Veisi, "LP-based over-sampled subband Adaptive Noise Canceller for speech enhancement in diffuse noise fields," in 9th International Conference on Signal Processing, ICSP'08, Beijing, China, 2008, pp. 157-161.

[67]    M. Bahrani, H. Sameti, N. Hafezi, and S. Momtazi, "A New Word Clustering Method for Building N-Gram Language Models in Continuous Speech Recognition Systems," in Lecture Notes in Computer Science, Proceedings of IEA/AIE 2008, 18-20 June, Wroclaw, Poland, 2008, pp. 286-293.

[68]    M. Bahrani, H. Sameti, N. Hafezi, and S. Momtazi, "Automatic word clustering based on grammar for Persian continuous speech recognition systems," in 13th International CSI Computer Conference, CSICC 2008, March 9-11, Kish Island, Iran, 2008, p. (In Persian).

[69]    B. Babaali, H. Sameti, and H. Veisi, "Using vocal tract length normalization in a HMM-based Persian continuous speech recognition system," in 13th International CSI Computer Conference, CSICC 2008, March 9-11, Kish Island, Iran, 2008, p. (In Persian).

[70]    B. BabaAli, H. Sameti, and M. Safayani, "Spectral Subtraction in Likelihood-Maximizing Framework for Robust Speech Recognition," in Interspeech 2008, 22-26 September, Brisbane, Australia, 2008, pp. 980-983.

[71]    B. BabaAli, H. Sameti, and M. Safayani, "Spectral subtraction in Model Distance Maximizing framework for robust speech recognition," in 9th International Conference on Signal Processing,  ICSP'08, 26-29 October, Beijing, China, 2008, pp. 627-630.

[72]    A. Asaei, M. J. Taghizadeh, and H. Sameti, "Far-field continuous speech recognition system based on speaker Localization and sub-band Beamforming," in Computer Systems and Applications, 2008. AICCSA 2008. IEEE/ACS International Conference on, Doha, Qatar, 2008, pp. 495-500.

[73]    B. Abbassi, H. Sameti, B. Babaali, and M. Bahrani, "Pronunciation variation modeling in a Persian continuous speech recognition system," in 13th International CSI Computer Conference, CSICC 2008, Kish Island, Iran, March 9-11, , Kish Island, Iran, 2008, p. (In Persian).

[74]    H. Veisi and H. Sameti, "Noise and speaker robustness in a Persian continuous speech recognition system," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, Sharjah, UAE, 2007, pp. 1-4.

[75]    S. Vaisipour, B. Babaali, and H. Sameti, "Using and evaluating new confidence measures in word-based isolated word recognizers," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, Sharjah, UAE, 2007, pp. 1-4.

[76]    H. Sajedi, H. Sameti, H. Beigi, and B. Babaali, "Discriminative training of hidden Markov models using PSO algorithm," in 12th Annual Computer Society of Iran Computer Conference (CSICC07), February 20-22, Tehran, Iran, 2007, pp. 295-302 (In Persian).

[77]    H. Sajedi, M. Jamzad, H. Sameti, and B. Babaali, "A clustering method for recognition of online Farsi letters using hidden Markov models," in 12th Annual Computer Society of Iran Computer Conference (CSICC07), February 20-22, Tehran, Iran, 2007, pp. 419-426 (In Persian).

[78]    M. Safayani, H. Sameti, B. Babaali, and M. T. Manzuri Shalmani, "An efficient multi-band spectral subtraction method for robust speech recognition," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, Sharjah, UAE, 2007, pp. 1-4.

[79]    M. Safayani, H. Sameti, B. Babaali, and M. T. Manzuri, "Adaptation of spectral subtraction for improving the performance of speech recognition systems," in 12th Annual Computer Society of Iran Computer Conference (CSICC07), February 20-22, Tehran, Iran, 2007, pp. 338-343 (In Persian).

[80]    M. Safayani, B. Babaali, M. T. M. Shalmani, H. Sameti, and S. Khaleghi, "Compensation of Channel and Noise Distortions Combining Maximum Likelihood based Spectral Subtraction and Normalization," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, February 12-15, Sharjah, UAE, 2007, pp. 508-511.

[81]    S. Momtazi, H. Sameti, S. Vaisipour, and M. Tefagh, "Introducing a Framework to Create Telephony Speech Databases from Direct Ones," in 14th International Conference on Systems, Signals and Image Processing, 2007 and 6th EURASIP Conference focused on Speech and Image Processing, Multimedia Communications and Services. , Maribor, Slovenia, 2007, pp. 327-330.

[82]    S. Momtazi, H. Sameti, M. Fazel-Zarandi, and M. Bahrani, "Robust parsing for word lattices in Continuous Speech Recognition systems," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, Sharjah, UAE, 2007, pp. 1-4.

[83]    S. Momtazi, H. Sameti, M. Bahrani, and N. Hafezi, "A POS-based fuzzy word clustering algorithm for continuous speech recognition systems," in IEEE 9th International Symposium on Signal Processing and Its Applications,  ISSPA 2007, Sharjah, UAE, 2007, pp. 1-4.

[84]    S. Momtazi, H. Sameti, M. Bahrani, and N. Hafezi, "A fuzzy word clustering approach for for building statistical language models," in 12th Annual Computer Society of Iran Computer Conference (CSICC07), February 20-22, Tehran, Iran, 2007, pp. 508-512 (In Persian).

[85]    A. Karimi, H. Sameti, and F. Amin, "A Proposed Criterion for the Quality Assessment of Watermarked Images Based on the Human Visual System," in 15th Iranian Conference on Electrical Engineering, Tehran, Iran, 2007, p. (In Persian).

[86]    A. Jalali, S. M. Moosavi, H. Sameti, and H. Rabiee, "Improving the Performance of Generalized Side-lobe Canceller Method in Speech Enhancement," in 15th Iranian Conference on Electrical Engineering, Tehran, Iran, 2007.

[87]    A. Asaei, H. Sameti, H. Rabiee, and M. Taghizadeh, "Robust Recognition of Persian Speech based on Speaker Localization and Beam Forming in Subband using Microphone Array," in 15th Iranian Conference on Electrical Engineering, Tehran, Iran, 2007.

[88]    A. Asaei, H. Sameti, and M. S. Moeen, "Robust speaker localization using beamforming and a new harmonic-based filter," in 12th Annual Computer Society of Iran Computer Conference (CSICC07), February 20-22, Tehran, Iran, 2007, pp. 359-364 (In Persian).

[89]    H. Veisi, H. Sameti, B. Babaali, K. Hosseinzadeh, and M. T. Manzuri, "Improving the Robustness of Persian Large Vocabulary Continuous Speech Recognition System for Real Applications," in IEEE 2nd Conference on Information and Communication Technologies: from Theory to Applications, ICTTA '06, Damascus, Syria, 2006, pp. 1293-1297.

[90]    S. Sharifi, M. Habibi, H. Rahimzadeh, M. Jamzad, and H. Sameti, "Face Animation Learning for Persian Speech Based on 3D Face Tracking," in 11th Annual Computer Society of Iran Computer Conference (CSICC06), January 24-26, Tehran, Iran, 2006, pp. 874-878 (In Persian).

[91]    H. Sajedi, B. Babaali, and H. Sameti, "Incorporating the Genetic algorithm techniques in the training process of a speech recognition system," in The 14th Iranian Conference in Electrical Engineering (ICEE), 2006.

[92]    M. Safayani, B. Babaali, H. Sameti, and H. R. Abutalebi, "Experiments of Distant Talking Command Speech Recognition Based on a Microphone Array and Robustness Methods," in IEEE 2nd Conference on Information and Communication Technologies: from Theory to Applications, ICTTA '06, Damascus, Syria, 2006, pp. 1236-1241.

[93]    N. Montazeri, G. Ghassem-Sani, and H. Sameti, "A fast and robust parser based on the Viterbi algorithm," in 11th Annual Computer Society of Iran Computer Conference (CSICC06), January 24-26, Tehran, Iran, 2006, pp. 473-478.

[94]    S. Momtazi, M. Fazel Zarandi, H. Sameti, and M. Bahrani, "Using a Partial Robust Parser in Continuous Speech Recognition Systems," in 11th Annual Computer Society of Iran Computer Conference (CSICC06), January 24-26, Tehran, Iran, 2006, pp. 810-814 (In Persian).

[95]    M. Bahrani, H. Sameti, N. Hafezi, and H. Movasagh, "Building and Incorporating Language Models for Persian continuous speech Recognition system " in The fifth international conference on Language Resources and Evaluation (LREC), Genoa, Italy, 2006.

[96]    H. Veisi, H. Sameti, and H. R. Abutalebi, "On the using of Principal Component Analysis on the Farsi Continuous Speech Recognition for Feature Robustness and Feature Reductions," in 10th Annual Computer Society of Iran Computer Conference (CSICC05), Tehran-Iran, 2005, pp. 242-251.

[97]    H. Veisi, A. Fazel Dehkordi, and H. Sameti, "Increasing the digit recognition rate in noise using noise robust features," in 13th Iranian Conference on Electrical Engineering (ICEE 2005), Zanjan, Iran, 2005.

[98]    M. Sabetian and H. Sameti, "Data Hiding in Speech Using FFT Coefficients," in 10th Annual Computer Society of Iran Conference (CSICC05), February 15-17, Tehran, Iran, 2005, pp. 270-279 (In Persian).

[99]    H. Movasagh and H. Sameti, "Two-step synchronous phoneme based search for continuous speech recognition," in First International Conference on Modeling, Simulation, and Applied Optimization (ICMSA0/05), Sharjah, U.A.E, 2005.

[100]  R. Halavati, S. Bagheri Shouraki, H. Sameti, S. Haratizadeh, and B. Babaali, "A Novel Noise Immune Speech Recognition Approach," in 11th International Fuzzy Sets Association (IFSA) World Congress, Beijing, China, 2005, pp. 972-976.

[101]  N. Hafezi, M. Bahrani, H. Movasagh, and H. Sameti, "Extracting Statistical Language Models for Continuous Speech Recognition Systems Using Persian Text Corpus," in 7th Conference of Intelligent Systems, Tehran, Iran, 2005.

[102]  A. Fazel Dehkordi, H. Sameti, and M. T. Manzoori, "Introducing a new robust feature of root mean cepstral coefficients and comparison of robust feature based methods in the presence of telephone line noise," in 10 Annual Computer Society of Iran Conference (CSICC05), February 15-17, Tehran, Iran, 2005, pp. 260-269 (In Persian).

[103]  A. Fazel Dehkordi, H. Sameti, and S. K. A. Ghiathi, "A New Feature Extraction Motivated by Human Ear," in First International Conference on Modeling, Simulation and Applied Optimization, ICMSA0/05, Sharjah, UAE, 2005, pp. 1-4.

[104]  A. Fazel Dehkordi, H. Sameti, and M. Bahrani, "Designing and Preparing of FARSI Connected Digit Database and Using it in a Word Based Automatic Speech Recognition System " in 13th Iranian Conference on Electrical Engineering, Zanjan, Iran, 2005.

[105]  M. Bahrani, B. Babaali, and H. Sameti, "Using language models in continuous Persian speech recognition," in 7th Conference of Intelligent Systems, Tehran, Iran, 2005.

[106]  B. Babaali, M. Bahrani, H. beigi, and H. Sameti, "Telephony Isolated Digit Recognition using Support Vector Machine," in 7th Conference of Intelligent Systems, Tehran, Iran, 2005.

[107]  B. Babaali, M. R. Bagheri, K. Hosseinzadeh, M. Bahrani, and H. Sameti, "A phoneme to word decoder based on lexicon tree for Persian speech recognition " in 10th Annual Computer Society of Iran Computer Conference (CSICC05), February 15-17, Tehran, Iran, 2005, pp. 321-329 (In Persian).

[108]  H. Sameti, H. Movasagh, B. Babaali, M. Bahrani, K. Hosseinzadeh, A. Fazel Dehkordi, et al., " Large Vocabulary Persian Speech Recognition System " in The 1st workshop on Persian language and computer, Tehran, Iran, 2004.

[109]  K. Hosseinzadeh, H. Sameti, H. R. Abutalebi, and A. Fazel Dehkordi, "MLLR method for environmental adaptation in the continuous FARSI speech recognition," in The 6th Conference on Intelligent Systems, November 26-27, Kerman, Iran, 2004.

[110]  B. Babaali and H. Sameti, "The Sharif Speaker-Independent Large Vocabulary Speech Recognition System," in The 2nd Workshop on Information Technology & Its Disciplines (WITID 2004), Kish, Iran, 2004, pp. 24-26.

[111]  H. Jahani, H. Sameti, and N. H. Gharavi, "Introducing a new attach on the stop/go waterfall system with more than 10 steps," in 2nd Iranian Society of Cryptology Conference, Tehran, Iran, 2003.

[112]  N. Gharavi, H. Sameti, and A. Ghaemi Bafghi, "New method of dual transfers for optimum implementation of LFSRs in software applications," in 8th International CSI Computer Conference, CSICC03, February 25-27, Ferdowsi University, Mashad, Iran, 2003, pp. 298-304 (In Persian).

[113]  H. Sameti, M. A. Ghafoorian, M. Bijankhan, S. A. Seyyedsalehi, and J. Sheikhzadegan, "Incorporating Training Capability in SHENAVA Farsi Speech Recognition System to Increase System Performance in Speaker-Dependent Applications," in First EurAsian Conference on Advances in Information and Communication Technology, October 29-31, Shiraz, Iran, 2002.

[114]  H. Sameti and M. A. Ghafoorian, "Automatic Phoneme Endpoint Detection Using HMM and Viterbi Segmentation " in First EurAsian Conference on Advances in Information and Communication Technology, October 29-31, Shiraz, Iran, 2002.

[115]  F. Almasganj, S. A. Seyedsalehi, M. Bijankhan, H. Sameti, and J. Sheikhzadegan, "SHENAVA-1 a Farsi Spontaneous Speech Recognition System," in Proceedings of ICEE 2001, 2001.

[116]  H. Sheikhzadeh, R. L. Brennan, and H. Sameti, "Real-time implementation of HMM-based MMSE algorithm for speech enhancement in hearing aid applications," in Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., International Conference on, Detroit, USA, 1995, pp. 808-811 vol.1.

[117]  L. Deng, G. Ramsay, and H. Sameti, "From modeling surface phenomena to modeling mechanisms: Towards a faithful model of the speech process aiming at speech recognition," in 1995 IEEE Workshop on Automatic Speech Recognition, Snowbird, Utah, 1995, pp. 183-184.

[118]  L. Deng, J. Nu, and H. Sameti, "Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units," in Acoustics, Speech, and Signal Processing, 1995. ICASSP-95., 1995 International Conference on, Detroit, USA, 1995, pp. 385-388.

[119]  H. Sheikhzadeh, H. Sameti, L. Deng, and R. L. Brennan, "Comparative performance of spectral subtraction and HMM-based speech enhancement strategies with application to hearing and design," in Acoustics, Speech, and Signal Processing, ICASSP-94., 1994 IEEE International Conference on, Adelaide, Australia, 1994, pp. I/13-I/16 vol.1.

[120]  L. Deng and H. Sameti, "Automatic Speech Recognition Using Dynamically Defined Speech Units," in Third International Conference on Spoken Language Processing, ICSLP94, Yokohama, Japan, 1994.

 

 

Books:

 

1. H. Sameti and M. Bijankhan, Persian Language and Computer, Volume 1, SAMT, 2010, 623 pages (In Persian).

2. H. Sameti and M. Bijankhan, Persian Language and Computer, Volume 2, SAMT, 2010, 671 pages (In Persian).

 

 

 

 

 

 :: Courses

 

 

  • Speech Recognition, graduate
  • Speech Processing,  graduate
  • Digital Signal Processing, graduate
  • Speech Enhancement,  graduate
  • Probability and Statistics, undergraduate
  • Signals and Systems, undergraduate

 

 

 

 :: Students

 

 

Ph.D. Students:

 

 

 

  • Hossein Zeinali
  • Hossein Hadian
  • Nooshin Maghsoodi
  • Elahe Najkar
  • Elham Seifossadat
  • Saeedreza Shehnehpoor 

 

 

 

 

 

 

 :: Speech Processing Lab (SPL)

 

 

SPL is a research laboratory of the Department of Computer Engineering at Sharif University Of Technology. The main area of the research in this lab is speech and language processing. Automatic speech recognition is a major field of research of this group and a speech recognition engine including the latest algorithms is developed. This engine is customized for the Persian language including Persian language models (statistical and grammatical) and the first version is released as NEVISA, the most robust and accurate Persian dictation system. SPL also developed NEWSHA, the high performance Persian telephony IVR and is expanding it towards a complete spoken dialogue system. The research fields of this group are:

  • Digital Speech Processing
  • Robust Speech Recognition
  • Spoken Dialogue Systems
  • Speech Synthesis (Text-To-Speech)
  • Speech Enhancement
  • Natural Language Modeling
  • Speech Database Design
  • Pattern Recognition

More information about this group is available in spl.ce.sharif.edu.