Hossein Sameti

120 papers A 6B 3C 5Misc 5Journal 54Unranked 47

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Toward IIT-Inspired Consciousness in LLMs: A Reward-Based Learning Framework. CoRR Hamid Reza Akbari, Mohammad Hossein Sameti, Amir M. Mansourian, Mohammad Hossein Rohban, Hossein Sameti
2025	J	`jnl`	Accent-Invariant Automatic Speech Recognition via Saliency-Driven Spectrogram Masking. CoRR Mohammad Hossein Sameti, Sepehr Harfi Moridani, Ali Zarean, Hossein Sameti
2025	J	`jnl`	Improving Direct Persian-English Speech-to-Speech Translation with Discrete Units and Synthetic Parallel Data. CoRR Sina Rashidi, Hossein Sameti
2025	J	`jnl`	Incorporating Error Level Noise Embedding for Improving LLM-Assisted Robustness in Persian Speech Recognition. CoRR Zahra Rahmani, Hossein Sameti
2025	J	`jnl`	ParsiPy: NLP Toolkit for Historical Persian Texts in Python. CoRR Farhan Farsi, Parnian Fazel, Sepand Haghighi, Sadra Sabouri, Farzaneh Goshtasb, Nadia Hajipour, Ehsaneddin Asgari, Hossein Sameti
2024	J	`jnl`	Data-to-text generation using conditional generative adversarial with enhanced transformer. Nat. Lang. Eng. Elham Seifossadat, Hossein Sameti
2024	—	`conf`	GE2PE: Persian End-to-End Grapheme-to-Phoneme Conversion. EMNLP (Findings) Elnaz Rahmati, Hossein Sameti
2024	—	`conf`	HalluSafe at SemEval-2024 Task 6: An NLI-based Approach to Make LLMs Safer by Better Detecting Hallucinations and Overgeneration Mistakes. SemEval@NAACL Zahra Rahimi, Hamidreza Amirzadeh, Alireza Sohrabi, Zeinab Taghavi, Hossein Sameti
2024	J	`jnl`	Improving semantic coverage of data-to-text generation model using dynamic memory networks. Nat. Lang. Eng. Elham Seifossadat, Hossein Sameti
2024	—	`conf`	NIMZ at SemEval-2024 Task 9: Evaluating Methods in Solving Brainteasers Defying Commonsense. SemEval@NAACL Zahra Rahimi, Mohammad Moein Shirzady, Zeinab Taghavi, Hossein Sameti
2024	—	`conf`	SLPL SHROOM at SemEval2024 Task 06 : A comprehensive study on models ability to detect hallucination. SemEval@NAACL Pouya Fallah, Soroush Gooran, Mohammad Jafarinasab, Pouya Sadeghi, Reza Farnia, Amirreza Tarabkhah, Zeinab Sadat Taghavi, Hossein Sameti
2024	J	`jnl`	SLPL SHROOM at SemEval2024 Task 06: A comprehensive study on models ability to detect hallucination. CoRR Pouya Fallah, Soroush Gooran, Mohammad Jafarinasab, Pouya Sadeghi, Reza Farnia, Amirreza Tarabkhah, Zainab Sadat Taghavi, Hossein Sameti
2024	—	`conf`	Sharif-MGTD at SemEval-2024 Task 8: A Transformer-Based Approach to Detect Machine Generated Text. SemEval@NAACL Seyedeh Fatemeh Ebrahimi, Karim Akhavan Azari, Amirmasoud Iravani, Arian Qazvini, Pouya Sadeghi, Zeinab Taghavi, Hossein Sameti
2024	J	`jnl`	Sharif-MGTD at SemEval-2024 Task 8: A Transformer-Based Approach to Detect Machine Generated Text. CoRR Seyedeh Fatemeh Ebrahimi, Karim Akhavan Azari, Amirmasoud Iravani, Arian Qazvini, Pouya Sadeghi, Zeinab Sadat Taghavi, Hossein Sameti
2024	—	`conf`	Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations. SemEval@NAACL Seyedeh Fatemeh Ebrahimi, Karim Akhavan Azari, Amirmasoud Iravani, Hadi Alizadeh, Zeinab Taghavi, Hossein Sameti
2024	J	`jnl`	Sharif-STR at SemEval-2024 Task 1: Transformer as a Regression Model for Fine-Grained Scoring of Textual Semantic Relations. CoRR Seyedeh Fatemeh Ebrahimi, Karim Akhavan Azari, Amirmasoud Iravani, Hadi Alizadeh, Zeinab Sadat Taghavi, Hossein Sameti
2023	—	`conf`	A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion. Tiny Papers @ ICLR Zeinab Sadat Taghavi, Ali Satvaty, Hossein Sameti
2023	J	`jnl`	A Change of Heart: Improving Speech Emotion Recognition through Speech-to-Text Modality Conversion. CoRR Zeinab Sadat Taghavi, Ali Satvaty, Hossein Sameti
2023	—	`conf`	Ebhaam at SemEval-2023 Task 1: A CLIP-Based Approach for Comparing Cross-modality and Unimodality in Visual Word Sense Disambiguation. SemEval@ACL Zeinab Taghavi, Parsa Haghighi Naeini, Mohammad Ali Sadraei Javaheri, Soroush Gooran, Ehsaneddin Asgari, Hamidreza Rabiee, Hossein Sameti
2023	J	`jnl`	Imaginations of WALL-E : Reconstructing Experiences with an Imagination-Inspired Module for Advanced AI Systems. CoRR Zeinab Sadat Taghavi, Soroush Gooran, Seyed Arshan Dalili, Hamidreza Amirzadeh, Mohammad Jalal Nematbakhsh, Hossein Sameti
2023	J	`jnl`	Learn What NOT to Learn: Towards Generative Safety in Chatbots. CoRR Leila Khalatbari, Yejin Bang, Dan Su, Willy Chung, Saeed Ghadimi, Hossein Sameti, Pascale Fung
2023	J	`jnl`	PCoQA: Persian Conversational Question Answering Dataset. CoRR Hamed Hematian Hemati, Atousa Toghyani, Atena Souri, Sayed Hesam Alavian, Hossein Sameti, Hamid Beigy
2023	—	`conf`	SUTNLP at SemEval-2023 Task 10: RLAT-Transformer for explainable online sexism detection. SemEval@ACL Hamed Hematian Hemati, Sayed Hesam Alavian, Hamid Beigy, Hossein Sameti
2023	—	`conf`	SUTNLP at SemEval-2023 Task 4: LG-Transformer for Human Value Detection. SemEval@ACL Hamed Hematian Hemati, Sayed Hesam Alavian, Hossein Sameti, Hamid Beigy
2022	—	`conf`	Docalog: Multi-document Dialogue System using Transformer-based Span Retrieval. DialDoc@ACL Sayed Hesam Alavian, Ali Satvaty, Sadra Sabouri, Ehsaneddin Asgari, Hossein Sameti
2022	J	`jnl`	Multi-Module G2P Converter for Persian Focusing on Relations between Words. CoRR Mahdi Rezaei, Negar Nayeri, Saeed Farzi, Hossein Sameti
2022	J	`jnl`	Stochastic Data-to-Text Generation Using Syntactic Dependency Information. Comput. Speech Lang. Elham Seifossadat, Hossein Sameti
2022	J	`jnl`	naab: A ready-to-use plug-and-play corpus for Farsi. CoRR Sadra Sabouri, Elnaz Rahmati, Soroush Gooran, Hossein Sameti
2021	J	`jnl`	Semi-supervised parallel shared encoders for speech emotion recognition. Digit. Signal Process. Yousef Pourebrahim, Farbod Razzazi, Hossein Sameti
2020	J	`jnl`	Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification. CoRR Ehsan Doostmohammadi, Hossein Sameti, Ali Saffar
2020	J	`jnl`	PerKey: A Persian News Corpus for Keyphrase Extraction and Generation. CoRR Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
2020	J	`jnl`	Persian Keyphrase Generation Using Sequence-to-Sequence Models. CoRR Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
2020	—	`conf`	Persian Sentiment Analysis Without Training Data Using Cross-Lingual Word Embeddings. IST Mohammad Aliramezani, Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
2020	J	`jnl`	Replay spoofing countermeasure using autoencoder and siamese networks on ASVspoof 2019 challenge. Comput. Speech Lang. Mohammad Adiban, Hossein Sameti, Saeedreza Shehnepoor
2020	J	`jnl`	Stochastic Natural Language Generation Using Dependency Information. CoRR Elham Seifossadat, Hossein Sameti
2020	—	`conf`	Training Doc2Vec on a Corpus of Persian Poems to Answer Thematic Similarity Multiple-Choice Questions. IST Soroosh Akef, Mohammad Hadi Bokaei, Hossein Sameti
2019	—	`conf`	Ghmerti at SemEval-2019 Task 6: A Deep Word- and Character-based Approach to Offensive Language Identification. SemEval@NAACL-HLT Ehsan Doostmohammadi, Hossein Sameti, Ali Saffar
2019	J	`jnl`	Replay Spoofing Countermeasure Using Autoencoder and Siamese Network on ASVspoof 2019 Challenge. CoRR Mohammad Adiban, Hossein Sameti, Saeedreza Shehnepoor
2019	J	`jnl`	Speaker Recognition With Random Digit Strings Using Uncertainty Normalized HMM-Based i-Vectors. IEEE ACM Trans. Audio Speech Lang. Process. Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali, Themos Stafylakis
2019	J	`jnl`	Speaker Recognition with Random Digit Strings Using Uncertainty Normalized HMM-based i-vectors. CoRR Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali, Themos Stafylakis
2018	—	`conf`	DeepMine Speech Processing Database: Text-Dependent and Independent Speaker Verification and Speech Recognition in Persian and English. Odyssey Hossein Zeinali, Hossein Sameti, Themos Stafylakis
2018	A	`conf`	End-to-end Speech Recognition Using Lattice-free MMI. INTERSPEECH Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur
2018	J	`jnl`	Flat-Start Single-Stage Discriminatively Trained HMM-Based Models for ASR. IEEE ACM Trans. Audio Speech Lang. Process. Hossein Hadian, Hossein Sameti, Daniel Povey, Sanjeev Khudanpur
2018	—	`conf`	Improving LF-MMI Using Unconstrained Supervisions for ASR. SLT Hossein Hadian, Daniel Povey, Hossein Sameti, Jan Trmal, Sanjeev Khudanpur
2018	—	`conf`	PerKey: A Persian News Corpus for Keyphrase Extraction and Generation. IST Ehsan Doostmohammadi, Mohammad Hadi Bokaei, Hossein Sameti
2018	—	`conf`	Spoken Pass-Phrase Verification in the i-vector Space. Odyssey Hossein Zeinali, Lukás Burget, Hossein Sameti, Honza Cernocký
2018	J	`jnl`	Spoken Pass-Phrase Verification in the i-vector Space. CoRR Hossein Zeinali, Lukás Burget, Hossein Sameti, Jan Cernocký
2017	J	`jnl`	HMM-Based Phrase-Independent i-Vector Extractor for Text-Dependent Speaker Verification. IEEE ACM Trans. Audio Speech Lang. Process. Hossein Zeinali, Hossein Sameti, Lukás Burget
2017	A	`conf`	Phone Duration Modeling for LVCSR Using Neural Networks. INTERSPEECH Hossein Hadian, Daniel Povey, Hossein Sameti, Sanjeev Khudanpur
2017	—	`conf`	SUT Submission for NIST 2016 Speaker Recognition Evaluation: Description and Analysis. ROCLING Hossein Zeinali, Hossein Sameti, Nooshin Maghsoodi
2017	—	`conf`	SUT System Description for Anti-Spoofing 2017 Challenge. ROCLING Mohammad Adiban, Hossein Sameti, Nooshin Maghsoodi, Sajjad Shahsavari
2017	J	`jnl`	SUT System Description for NIST SRE 2016. CoRR Hossein Zeinali, Hossein Sameti, Nooshin Maghsoodi
2017	J	`jnl`	Text-dependent speaker verification based on i-vectors, Neural Networks and Hidden Markov Models. Comput. Speech Lang. Hossein Zeinali, Hossein Sameti, Lukás Burget, Jan Cernocký
2016	—	`conf`	Deep Neural Networks and Hidden Markov Models in i-vector-based Text-Dependent Speaker Verification. Odyssey Hossein Zeinali, Lukás Burget, Hossein Sameti, Ondrej Glembek, Oldrich Plchot
2016	J	`jnl`	Extractive summarization of multi-party meetings through discourse segmentation. Nat. Lang. Eng. Mohammad Hadi Bokaei, Hossein Sameti, Yang Liu
2016	B	`conf`	Localized discriminative Gaussian process latent variable model for text-dependent speaker verification. ESANN Nooshin Maghsoodi, Hossein Sameti, Hossein Zeinali
2016	J	`jnl`	Summarizing Meeting Transcripts Based on Functional Segmentation. IEEE ACM Trans. Audio Speech Lang. Process. Mohammad Hadi Bokaei, Hossein Sameti, Yang Liu
2016	A	`conf`	i-Vector/HMM Based Text-Dependent Speaker Verification System for RedDots Challenge. INTERSPEECH Hossein Zeinali, Hossein Sameti, Lukás Burget, Jan Cernocký, Nooshin Maghsoodi, Pavel Matejka
2015	A	`conf`	Extractive meeting summarization through speaker zone detection. INTERSPEECH Mohammad Hadi Bokaei, Hossein Sameti, Yang Liu
2015	J	`jnl`	Hidden Markov model-based speech enhancement using multivariate Laplace and Gaussian distributions. IET Signal Process. Ali Aroudi, Hadi Veisi, Hossein Sameti
2015	J	`jnl`	Linear Discourse Segmentation of Multi-Party Meetings Based on Local and Global Information. IEEE ACM Trans. Audio Speech Lang. Process. Mohammad Hadi Bokaei, Hossein Sameti, Yang Liu
2015	J	`jnl`	Non-speaker information reduction from Cosine Similarity Scoring in i-vector based speaker verification. Comput. Electr. Eng. Hossein Zeinali, Alireza Mirian, Hossein Sameti, Bagher BabaAli
2015	J	`jnl`	Soft context clustering for F0 modeling in HMM-based speech synthesis. EURASIP J. Adv. Signal Process. Soheil Khorram, Hossein Sameti, Simon King
2015	—	`conf`	Speaker models reduction for optimized telephony text-prompted speaker verification. CCECE Elaheh Kalantari, Hossein Sameti, Hossein Zeinali
2015	J	`jnl`	Speech signal modeling using multivariate distributions. EURASIP J. Audio Speech Music. Process. Ali Aroudi, Hadi Veisi, Hossein Sameti, Zahra Mafakheri
2015	Misc	`conf`	Telephony text-prompted speaker verification using i-vector representation. ICASSP Hossein Zeinali, Elaheh Kalantari, Hossein Sameti, Hossein Hadian
2015	—	`conf`	Unsupervised approach to extract summary keywords in meeting domain. EUSIPCO Mohammad Hadi Bokaei, Hossein Sameti, Yang Liu
2014	B	`conf`	Active Learning in Noisy Conditions for Spoken Language Understanding. COLING Hossein Hadian, Hossein Sameti
2014	J	`jnl`	An evolutionary decoding method for HMM-based continuous speech recognition systems using particle swarm optimization. Pattern Anal. Appl. Negin Najkar, Farbod Razzazi, Hossein Sameti
2014	J	`jnl`	Context-dependent acoustic modeling based on hidden maximum entropy model for statistical parametric speech synthesis. EURASIP J. Audio Speech Music. Process. Soheil Khorram, Hossein Sameti, Fahimeh Bahmaninezhad, Simon King, Thomas Drugman
2013	—	`conf`	Average Voice Modeling Based on Unbiased Decision Trees. NOLISP Fahimeh Bahmaninezhad, Soheil Khorram, Hossein Sameti
2013	J	`jnl`	Speech enhancement using hidden Markov models in Mel-frequency domain. Speech Commun. Hadi Veisi, Hossein Sameti
2013	—	`conf`	Unsupervised Induction of Persian Semantic Verb Classes Based on Syntactic Information. IIS Maryam Aminian, Mohammad Sadegh Rasooli, Hossein Sameti
2012	J	`jnl`	A Novel Method For Speech Segmentation Based On Speakers' Characteristics CoRR Behrouz Abdolali, Hossein Sameti
2012	C	`conf`	A comparative study on single-channel noise estimation methods for speech enhancement. ISDA Hadi Veisi, Hossein Sameti
2012	—	`conf`	A fast two-level Speaker Identification method employing sparse representation and GMM-based methods. ISSPA Hossein Zeinali, Hossein Sameti, Hossein Khaki, Bagher BabaAli
2012	—	`conf`	Active learning of EHVS parser for Persian language understanding. IST Mohammad Amin Tajgardoon, Fattaneh Jabbari, Hossein Sameti, Sara Bahaadini
2012	—	`conf`	An optimum MMSE post-filter for Adaptive Noise Cancellation in automobile environment. ISSPA Soheil Khorram, Hossein Sameti, Hadi Veisi
2012	—	`conf`	Cepstral-domain HMM-based speech enhancement using vector Taylor series and parallel model combination. ISSPA Hadi Veisi, Hossein Sameti
2012	J	`jnl`	Hidden-Markov-model-based voice activity detector with high speech detection rate for speech enhancement. IET Signal Process. Hadi Veisi, Hossein Sameti
2012	A	`conf`	KNNDIST: A Non-Parametric Distance Measure for Speaker Segmentation. INTERSPEECH Seyed Hamidreza Mohammadi, Hossein Sameti, Mahsa Sadat Elyasi Langarani, Amirhossein Tavanaei
2012	—	`conf`	Speech enhancement based on hidden Markov model with discrete cosine transform coefficients using Laplace and Gaussian distributions. ISSPA Ali Aroudi, Hadi Veisi, Hossein Sameti
2012	—	`conf`	Support Vector Data Description for Spoken Digit Recognition. BIOSIGNALS Amirhossein Tavanaei, Alireza Ghasemi, Mohammad Tavanaei, Hossein Sameti, Mohammad Taghi Manzuri
2012	—	`conf`	The effect of phase information in speech enhancement and speech recognition. ISSPA Mahsa Sadat Elyasi Langarani, Hadi Veisi, Hossein Sameti
2011	J	`jnl`	A computational grammar for Persian based on GPSG. Lang. Resour. Evaluation Mohammad Bahrani, Hossein Sameti, Mehdi Hafezi Manshadi
2011	J	`jnl`	A large vocabulary continuous speech recognition system for Persian language. EURASIP J. Audio Speech Music. Process. Hossein Sameti, Hadi Veisi, Mohammad Bahrani, Bagher BabaAli, Khosro Hosseinzadeh
2011	—	`conf`	A parallel cepstral and spectral modeling for HMM-based speech enhancement. DSP Hadi Veisi, Hossein Sameti
2011	J	`jnl`	Building Statistical Language Models for Persian Continuous Speech Recognition Systems Using the Peykare Corpus. Int. J. Comput. Process. Orient. Lang. Mohammad Bahrani, Hossein Sameti
2011	—	`conf`	False alarm reduction by improved filler model and post-processing in speech keyword spotting. MLSP Amirhossein Tavanaei, Hossein Sameti, Seyed Hamidreza Mohammadi
2011	—	`conf`	Filter-bank design based on dependencies between frequency components and phoneme characteristics. EUSIPCO Seyed Hamidreza Mohammadi, Hossein Sameti, Amirhossein Tavanaei, Ali Soltani-Farani
2011	—	`conf`	Implementation and evaluation of statistical parametric speech synthesis methods for the Persian language. MLSP Sara Bahaadini, Hossein Sameti, Soheil Khorram
2011	—	`conf`	Persian language understanding using a two-step extended hidden vector state parser. MLSP Fattaneh Jabbari, Hossein Sameti, Mohammad Hadi Bokaei
2011	J	`jnl`	The integration of principal component analysis and cepstral mean subtraction in parallel model combination for robust speech recognition. Digit. Signal Process. Hadi Veisi, Hossein Sameti
2011	—	`conf`	Unilateral semi-supervised learning of extended hidden vector state for Persian Language Understanding. NLPKE Fattaneh Jabbari, Hossein Sameti, Mohammad Hadi Bokaei
2010	J	`jnl`	A New Bigram-PLSA Language Model for Speech Recognition. EURASIP J. Adv. Signal Process. Mohammad Bahrani, Hossein Sameti
2010	J	`jnl`	A novel approach to HMM-based speech recognition systems using particle swarm optimization. Math. Comput. Model. Negin Najkar, Farbod Razzazi, Hossein Sameti
2010	—	`conf`	Divided POMDP method for complex menu problems in spoken dialogue systems. SLT Maryam Habibi, Siavash Rahbar N., Hossein Sameti
2010	—	`conf`	On-line learning of a Persian spoken dialogue system using real training data. ISSPA Maryam Habibi, Hossein Sameti, Hesam Setareh
2009	C	`conf`	A Possibilistic Approach for Building Statistical Language Models. ISDA Saeedeh Momtazi, Hossein Sameti
2009	C	`conf`	An improved parallel model combination method for noisy speech recognition. ASRU Hadi Veisi, Hossein Sameti
2009	J	`jnl`	Likelihood-Maximizing-Based Multiband Spectral Subtraction for Robust Speech Recognition. EURASIP J. Adv. Signal Process. Bagher BabaAli, Hossein Sameti, Mehran Safayani
2008	C	`conf`	A New Word Clustering Method for Building N-Gram Language Models in Continuous Speech Recognition Systems. IEA/AIE Mohammad Bahrani, Hossein Sameti, Nazila Hafezi, Saeedeh Momtazi
2008	C	`conf`	Far-field continuous speech recognition system based on speaker Localization and sub-band Beamforming. AICCSA Afsaneh Asaei, Mohammad Javad Taghizadeh, Hossein Sameti
2008	Misc	`conf`	Nevisa, a Persian Continuous Speech Recognition System. CSICC Hossein Sameti, Hadi Veisi, Mohammad Bahrani, Bagher BabaAli, Khosro Hosseinzadeh
2008	J	`jnl`	Parental control based on speaker class verification. IEEE Trans. Consumer Electron. Sajad Shirali-Shahreza, Hossein Sameti, Mohammad Shirali-Shahreza
2008	A	`conf`	Spectral subtraction in likelihood-maximizing framework for robust speech recognition. INTERSPEECH Bagher BabaAli, Hossein Sameti, Mehran Safayani
2008	Misc	`conf`	The Combination of CMS with PMC for Improving Robustness of Speech Recognition Systems. CSICC Hadi Veisi, Hossein Sameti
2007	—	`conf`	A POS-based fuzzy word clustering algorithm for continuous speech recognition systems. ISSPA Saeedeh Momtazi, Hossein Sameti, Mohammad Bahrani, Nazila Hafezi
2007	—	`conf`	An efficient multi-band spectral subtraction method for robust speech recognition. ISSPA Mehran Safayani, Hossein Sameti, Bagher BabaAli, Mohammad Taghi Manzuri Shalmani
2007	—	`conf`	Noise and speaker robustness in a Persian continuous speech recognition system. ISSPA Hadi Veisi, Hossein Sameti
2007	—	`conf`	Robust parsing for word lattices in Continuous Speech Recognition systems. ISSPA Saeedeh Momtazi, Hossein Sameti, Maryam Fazel-Zarandi, Mohammad Bahrani
2007	—	`conf`	Using and evaluating new confidence measures in word-based isolated word recognizers. ISSPA Saman Vaisipour, Bagher BabaAli, Hossein Sameti
2006	B	`conf`	Building and Incorporating Language Models for Persian Continuous Speech Recognition Systems. LREC Mohammad Bahrani, Hossein Sameti, Nazila Hafezi, H. Movassagh
2002	J	`jnl`	Nonstationary-state hidden Markov model representation of speech signals for speech enhancement. Signal Process. Hossein Sameti, Li Deng
1998	J	`jnl`	HMM-based strategies for enhancement of speech signals embedded in nonstationary noise. IEEE Trans. Speech Audio Process. Hossein Sameti, Hamid Sheikhzadeh, Li Deng, Robert L. Brennan
1996	J	`jnl`	Transitional speech units and their representation by regressive Markov states: applications to speech recognition. IEEE Trans. Speech Audio Process. Li Deng, Hossein Sameti
1995	Misc	`conf`	Improved speech modeling and recognition using multi-dimensional articulatory states as primitive speech units. ICASSP Li Deng, J. Nu, Hossein Sameti
1995	Misc	`conf`	Real-time implementation of HMM-based MMSE algorithm for speech enhancement in hearing aid applications. ICASSP Hamid Sheikhzadeh, Robert L. Brennan, Hossein Sameti
1994	—	`conf`	Automatic speech recognition using dynamically defined speech units. ICSLP Li Deng, Hossein Sameti
1994	—	`conf`	Comparative performance of spectral subtraction and HMM-based speech enhancement strategies with application to hearing and design. ICASSP (1) Hamid Sheikhzadeh, Hossein Sameti, Li Deng, Robert L. Brennan