default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMohammad Mehdi Homayounpour
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2025
[j30]Omid Hajipoor, Ahmad Nickabadi, Mohammad Mehdi Homayounpour:
GPTGAN: Utilizing the GPT language model and GAN to enhance adversarial text generation. Neurocomputing 617: 128865 (2025)- 2024
- [j29]Mohammad Modiri, Mohammad Mehdi Ebadzadeh, Mohammad Mehdi Homayounpour:
Reservoir consisting of diverse dynamical behaviors and its application in time series classification. Int. J. Data Sci. Anal. 17(1): 75-92 (2024) - 2023
- [j28]Amir Mohammad Rostami
, Mohammad Mehdi Homayounpour, Ahmad Nickabadi:
Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection. Circuits Syst. Signal Process. 42(7): 4252-4270 (2023) - [j27]Mohammad Khalooei, Mohammad Mehdi Homayounpour, Maryam Amirmazlaghani:
Layer-wise regularized adversarial training using layers sustainability analysis framework. Neurocomputing 540: 126182 (2023) - [j26]Zahra Rahimi, Mohammad Mehdi Homayounpour:
The impact of preprocessing on word embedding quality: a comparative study. Lang. Resour. Evaluation 57(1): 257-291 (2023) - [j25]Mohammad Mahdi Mahsuli, Shahram Khadivi, Mohammad Mehdi Homayounpour:
LenM: Improving Low-Resource Neural Machine Translation Using Target Length Modeling. Neural Process. Lett. 55(7): 9435-9466 (2023) - [i9]Niloofar Ranjbar, Saeedeh Momtazi, Mohammad Mehdi Homayounpour:
Explaining Recommendation System Using Counterfactual Textual Explanations. CoRR abs/2303.11160 (2023) - 2022
- [j24]Mohammad Modiri, Mohammad Mehdi Homayounpour, Mohammad Mehdi Ebadzadeh:
Reservoir weights learning based on adaptive dynamic programming and its application in time series classification. Neural Comput. Appl. 34(16): 13201-13217 (2022) - [i8]Mohammad Khalooei, Mohammad Mehdi Homayounpour, Maryam Amirmazlaghani:
Layer-wise Regularized Adversarial Training using Layers Sustainability Analysis (LSA) framework. CoRR abs/2202.02626 (2022) - 2021
- [j23]Zahra Rahimi, Mohammad Mehdi Homayounpour:
TensSent: a tensor based sentimental word embedding method. Appl. Intell. 51(8): 6056-6071 (2021) - [i7]Amir Mohammad Rostami, Mohammad Mehdi Homayounpour, Ahmad Nickabadi:
Efficient Attention Branch Network with Combined Loss Function for Automatic Speaker Verification Spoof Detection. CoRR abs/2109.02051 (2021) - 2020
- [j22]Toktam Zoughi, Mohammad Mehdi Homayounpour, Mahmood Deypir:
Adaptive windows multiple deep residual networks for speech recognition. Expert Syst. Appl. 139 (2020) - [j21]Zahra Rahimi, Mohammad Mehdi Homayounpour:
Tens-embedding: A Tensor-based document embedding method. Expert Syst. Appl. 162: 113770 (2020)
2010 – 2019
- 2019
- [j20]Toktam Zoughi, Mohammad Mehdi Homayounpour:
DBMiP: A pre-training method for information propagation over deep networks. Comput. Speech Lang. 55: 82-100 (2019) - [j19]Amir Hossein Hadjahmadi, Mohammad Mehdi Homayounpour:
Robust feature extraction and uncertainty estimation based on attractor dynamics in cyclic deep denoising autoencoders. Neural Comput. Appl. 31(11): 7989-8002 (2019) - 2018
- [j18]Abbas Khosravani, Mohammad Mehdi Homayounpour:
Nonparametrically trained PLDA for short duration i-vector speaker verification. Comput. Speech Lang. 52: 105-122 (2018) - [j17]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Monaural multi-talker speech recognition using factorial speech processing models. Speech Commun. 98: 1-16 (2018) - [c30]Mahdieh Ramezani, Mohammad Mehdi Homayounpour:
Investigating the effect of phase reconstruction on the bandwidth extention on audio signal using DNNs. IST 2018: 544-548 - 2017
- [j16]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Feature joint-state posterior estimation in factorial speech processing models using deep neural networks. Comput. Electr. Eng. 62: 574-587 (2017) - [j15]Abbas Khosravani, Mohammad Mehdi Homayounpour:
A PLDA approach for language and text independent speaker recognition. Comput. Speech Lang. 45: 457-474 (2017) - [j14]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Modeling State-Conditional Observation Distribution Using Weighted Stereo Samples for Factorial Speech Processing Models. Circuits Syst. Signal Process. 36(1): 339-357 (2017) - [j13]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Erratum to: Modeling State-Conditional Observation Distribution Using Weighted Stereo Samples for Factorial Speech Processing Models. Circuits Syst. Signal Process. 36(1): 358 (2017) - [j12]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
Dynamic sparsity control in Deep Belief Networks. Intell. Data Anal. 21(4): 963-979 (2017) - [j11]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
Effective sparsity control in deep belief networks using normal regularization term. Knowl. Inf. Syst. 53(2): 533-550 (2017) - [c29]Abbas Khosravani, Mohammad Mehdi Homayounpour:
Nonparametrically Trained Probabilistic Linear Discriminant Analysis for i-Vector Speaker Verification. INTERSPEECH 2017: 1019-1023 - [i6]Mohaddeseh Bastan, Shahram Khadivi, Mohammad Mehdi Homayounpour:
Neural Machine Translation on Scarce-Resource Condition: A case-study on Persian-English. CoRR abs/1701.01854 (2017) - [i5]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Feature Joint-State Posterior Estimation in Factorial Speech Processing Models using Deep Neural Networks. CoRR abs/1707.02661 (2017) - 2016
- [c28]Abbas Khosravani, Mohammad Mehdi Homayounpour:
AUT System for SITW Speaker Recognition Challenge. INTERSPEECH 2016: 843-847 - [c27]Abbas Khosravani, Mohammad Mehdi Homayounpour, Dijana Petrovska-Delacrétaz, Gérard Chollet:
A PLDA Approach for Language and Text Independent Speaker Recognition. Odyssey 2016: 264-269 - [i4]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Monaural Multi-Talker Speech Recognition using Factorial Speech Processing Models. CoRR abs/1610.01367 (2016) - 2015
- [j10]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy. Int. J. Pattern Recognit. Artif. Intell. 29(5): 1551006:1-1551006:16 (2015) - [c26]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
Normal sparse Deep Belief Network. IJCNN 2015: 1-7 - [c25]Toktam Zoughi, Mohammad Mehdi Homayounpour:
Gender aware Deep Boltzmann Machines for phone recognition. IJCNN 2015: 1-5 - [i3]Mahdi Khademian, Mohammad Mehdi Homayounpour:
Modeling State-Conditional Observation Distribution using Weighted Stereo Samples for Factorial Speech Processing Models. CoRR abs/1503.02578 (2015) - 2014
- [c24]Abbas Khosravani, Mohammad Mehdi Homayounpour:
Linearly Constrained Minimum Variance for Robust I-vector Based Speaker Recognition. Odyssey 2014: 249-253 - [i2]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
A brief survey on deep belief networks and introducing a new object oriented MATLAB toolbox (DeeBNet). CoRR abs/1408.3264 (2014) - [i1]Mohammad Ali Keyvanrad, Mohammad Mehdi Homayounpour:
Deep Belief Network Training Improvement Using Elite Samples Minimizing Free Energy. CoRR abs/1411.4046 (2014) - 2013
- [j9]Mohammad Hossein Moattar, Mohammad Mehdi Homayounpour:
A unified framework for domain independent online speaker indexing in eigen-voice space using an index tree of reference models. Int. J. Speech Technol. 16(4): 381-401 (2013) - 2012
- [j8]Mohammad Hossein Moattar, Mohammad Mehdi Homayounpour:
Variational conditional random fields for online speaker detection and tracking. Speech Commun. 54(6): 763-780 (2012) - [j7]Mohammad Hossein Moattar, Mohammad Mehdi Homayounpour:
A review on speaker diarization systems and approaches. Speech Commun. 54(10): 1065-1103 (2012) - [c23]Mohammad Hadi Valipour, Mohammad Mehdi Homayounpour, M. Amin Mehralian:
Automatic digital modulation recognition in presence of noise using SVM and PSO. IST 2012: 378-382 - 2011
- [j6]Vahid Asadpour, Mohammad Mehdi Homayounpour, Farzad Towhidkhah:
Audio-visual speaker identification using dynamic facial movements and utterance phonetic content. Appl. Soft Comput. 11(2): 2083-2093 (2011) - [j5]Nooshin Maghsoodi, Mohammad Mehdi Homayounpour:
Improving Farsi multiclass text classification using a thesaurus and two-stage feature selection. J. Assoc. Inf. Sci. Technol. 62(10): 2055-2066 (2011) - [c22]Nooshin Maghsoodi, Mohammad Mehdi Homayounpour:
Using Thesaurus to Improve Multiclass Text Classification. CICLing (2) 2011: 244-253 - 2010
- [j4]Ali Sadeghi-Naini, Mohammad Mehdi Homayounpour, Abbas Samani:
A real-time trained system for robust speaker verification using relative space of anchor models. Comput. Speech Lang. 24(4): 545-561 (2010) - [c21]Mohammad Hossein Moattar, Mohammad Mehdi Homayounpour, Nima Khademi Kalantari:
A new approach for robust realtime Voice Activity Detection using spectral pattern. ICASSP 2010: 4478-4481
2000 – 2009
- 2009
- [j3]Jahanshah Kabudian, Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi:
Bernoulli versus Markov: Investigation of state transition regime in switching-state acoustic models. Signal Process. 89(4): 662-668 (2009) - [c20]S. A. Hosseini Amereii, Mohammad Mehdi Homayounpour:
Improvement of language Identification performance by Aggregated Phone Recognizer. EUSIPCO 2009: 1770-1773 - [c19]Mohammad Hossein Moattar, Mohammad Mehdi Homayounpour:
A simple but efficient real-time Voice Activity Detection algorithm. EUSIPCO 2009: 2549-2553 - 2008
- [c18]A. R. Khanteymoori, Mohammad Mehdi Homayounpour, Mohammad Bagher Menhaj:
A Bayesian Network Based Approach for Data Classification Using Structural Learning. CSICC 2008: 25-32 - [c17]Amir Hossein Hadjahmadi, Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi:
Robust weighted fuzzy c-means clustering. FUZZ-IEEE 2008: 305-311 - [c16]Jahanshah Kabudian, Mohammad Mehdi Homayounpour, Seyed Mohammad Ahadi:
Time-inhomogeneous hidden Bernoulli model: An alternative to hidden Markov model for automatic speech recognition. ICASSP 2008: 4101-4104 - [c15]Raheleh Makki, Mohammad Mehdi Homayounpour:
Word Sense Disambiguation of Farsi Homographs Using Thesaurus and Corpus. GoTAL 2008: 315-323 - 2007
- [j2]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour:
Features based on filtering and spectral peaks in autocorrelation domain for robust speech recognition. Comput. Speech Lang. 21(1): 187-205 (2007) - [c14]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour:
Improved Autocorrelation-based Noise robust speech recognition using kernel-based cross correlation and overestimation parameters. EUSIPCO 2007: 2355-2359 - [c13]Babak Nasersharif, Ahmad Akbari, Mohammad Mehdi Homayounpour:
Mel sub-band filtering and compression for robust speech recognition. INTERSPEECH 2007: 1102-1105 - [c12]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour, Amir Kashi:
Consideration of correlation between noise and clean speech signals in autocorrelation-based robust speech recognition. ISSPA 2007: 1-4 - [c11]Emad Bahrami Samani, Mohammad Mehdi Homayounpour, Hong Gu:
A Novel Hybrid GMM/SVM Architecture for Protein Secondary Structure Prediction. WILF 2007: 491-496 - 2006
- [j1]Vahid Asadpour, Farzad Towhidkhah, Mohammad Mehdi Homayounpour:
Performance enhancement for audio-visual speaker identification using dynamic facial muscle model. Medical Biol. Eng. Comput. 44(10): 919-930 (2006) - [c10]Babak Nasersharif, Ahmad Akbari, Mohammad Mehdi Homayounpour:
Spectral peaks enhancement for extracting robust speech features. EUSIPCO 2006: 1-5 - [c9]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour:
Use of Spectral Peaks in Autocorrelation and Group Delay Domains for Robust Speech Recognition. ICASSP (1) 2006: 517-520 - [c8]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour:
Robust feature extraction based on spectral peaks of group delay and autocorrelation function and phase domain analysis. INTERSPEECH 2006 - [c7]Mohammad Mehdi Homayounpour, Majid Namnabat:
Farsbayan: a unit selection based Farsi speech synthesizer. INTERSPEECH 2006 - [c6]Gholamreza Farahani, Seyed Mohammad Ahadi, Mohammad Mehdi Homayounpour:
Robust Feature Extraction of Speech Via Noise Reduction in Autocorrelation Domain. MRCS 2006: 466-473 - 2004
- [c5]Jahanshah Kabudian, Mohammad Reza Meybodi, Mohammad Mehdi Homayounpour:
Applying Continuous Action Reinforcement Learning Automata(CARLA) to Global Training of Hidden Markov Models. ITCC (2) 2004: 638-642 - 2002
- [c4]Mohammad Mehdi Homayounpour:
Speaker Model and Decision Threshold Updating in Speaker Verification. EurAsia-ICT 2002: 1-10
1990 – 1999
- 1995
- [c3]Mohammad Mehdi Homayounpour, Gérard Chollet:
Neural net approaches to speaker verification: comparison with second order statistic measures. ICASSP 1995: 353-356 - [c2]Mohammad Mehdi Homayounpour, Gérard Chollet:
Discrimination of voices of twins and siblings for speaker verification. EUROSPEECH 1995: 345-348 - 1993
- [c1]Mohammad Mehdi Homayounpour, Jean-Philippe Goldman, Gérard Chollet, Jacqueline Vaissière:
Performance comparison of machine and human speaker verification. EUROSPEECH 1993: 2295-2298
Coauthor Index
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-08 02:22 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
