P. Ghahremani

Most-cited papers

Purely Sequence-Trained Neural Networks for ASR Based on Lattice-Free MMI
D. Povey, Vijayaditya Peddinti, Daniel Galvez, P. Ghahremani +4 more
2016Interspeech895 citations
Semantic Scholar
Deep neural network-based speaker embeddings for end-to-end speaker verification
D. Snyder, P. Ghahremani, D. Povey, D. Garcia-Romero +2 more
2016Spoken Language Technology Workshop367 citations
Semantic Scholar
A pitch extraction algorithm tuned for automatic speech recognition
P. Ghahremani, B. BabaAli, D. Povey, Korbinian Riedhammer +2 more
2014IEEE International Conference on Acoustics, Speech, and Signal Processing351 citations
Semantic Scholar
A Time-Restricted Self-Attention Layer for ASR
D. Povey, Hossein Hadian, P. Ghahremani, Ke Li +1 more
2018IEEE International Conference on Acoustics, Speech, and Signal Processing163 citations
Semantic Scholar
Emotion Identification from Raw Speech Signals Using DNNs
Mousmita Sarma, P. Ghahremani, D. Povey, N. Goel +2 more
2018Interspeech125 citations
Semantic Scholar
Acoustic Modelling from the Signal Domain Using CNNs
P. Ghahremani, Vimal Manohar, D. Povey, S. Khudanpur
2016Interspeech93 citations
Semantic Scholar
Investigation of transfer learning for ASR using LF-MMI trained neural networks
P. Ghahremani, Vimal Manohar, Hossein Hadian, D. Povey +1 more
2017Automatic Speech Recognition & Understanding75 citations
Semantic Scholar
A Teacher-Student Learning Approach for Unsupervised Domain Adaptation of Sequence-Trained ASR Models
Vimal Manohar, P. Ghahremani, D. Povey, S. Khudanpur
2018Spoken Language Technology Workshop60 citations
Semantic Scholar
End-to-end Deep Neural Network Age Estimation
P. Ghahremani, P. S. Nidadavolu, Nan-Xin Chen, J. Villalba +3 more
2018Interspeech60 citations
Semantic Scholar
A keyword search system using open source software
J. Trmal, Guo-Guo Chen, D. Povey, S. Khudanpur +8 more
2014Spoken Language Technology Workshop45 citations Open access
Semantic Scholar
The Kaldi OpenKWS System: Improving Low Resource Keyword Search
J. Trmal, Matthew Wiesner, Vijayaditya Peddinti, Xiaohui Zhang +6 more
2017Interspeech40 citations
Semantic Scholar
Stability and size-dependency of temperature-related Cauchy–Born hypothesis
A. Khoei, P. Ghahremani, M. J. Abdolhosseini Qomi, P. Banihashemi
201125 citations
Semantic Scholar
Temperature-dependent multi-scale modeling of surface effects on nano-materials
A. Khoei, P. Ghahremani
201220 citations
Semantic Scholar
Linearly augmented deep neural network
P. Ghahremani, J. Droppo, M. Seltzer
2016IEEE International Conference on Acoustics, Speech, and Signal Processing17 citations
Semantic Scholar
Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Swayambhu Nath Ray, Minhua Wu, A. Raju, P. Ghahremani +6 more
2021Interspeech14 citations Open access
Semantic Scholar
An empirical evaluation of zero resource acoustic unit discovery
Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju +6 more
2017IEEE International Conference on Acoustics, Speech, and Signal Processing14 citations Open access
Semantic Scholar
Acoustic Modeling from Frequency Domain Representations of Speech
P. Ghahremani, Hossein Hadian, Hang Lv, D. Povey +1 more
2018Interspeech13 citations
Semantic Scholar
Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation
V. A. Trinh, P. Ghahremani, Brian King, J. Droppo +2 more
2022Interspeech9 citations Open access
Semantic Scholar
Multi‐scale modeling of surface effects in nano‐materials with temperature‐related Cauchy‐Born hypothesis via the modified boundary Cauchy‐Born model
A. Khoei, P. Ghahremani, H. DorMohammadi
20149 citations
Semantic Scholar
Prune Then Distill: Dataset Distillation with Importance Sampling
Anirudh S. Sundar, Gokce Keskin, Chander Chandak, I-Fan Chen +2 more
2023IEEE International Conference on Acoustics, Speech, and Signal Processing8 citations
Semantic Scholar
Improving Emotion Identification Using Phone Posteriors in Raw Speech Waveform Based DNN
Mousmita Sarma, P. Ghahremani, D. Povey, N. Goel +2 more
2019Interspeech8 citations
Semantic Scholar
Self-stabilized deep neural network
P. Ghahremani, J. Droppo
2016IEEE International Conference on Acoustics, Speech, and Signal Processing8 citations
Semantic Scholar
Hot-Fixing Wake Word Recognition for End-to-End ASR Via Neural Model Reprogramming
Pin-Jui Ku, I-Fan Chen, Chao-Han Huck Yang, A. Raju +6 more
2024IEEE International Conference on Acoustics, Speech, and Signal Processing4 citations
Semantic Scholar
Muse Spark Safety&Preparedness Report
Cristina Menghini, Peter Ney, Hamza Kwisaba, Zifan Wang +115 more
20261 citations
Semantic Scholar
Removing redundancy from lattices
David Nolden, H. Soltau, D. Povey, P. Ghahremani +2 more
2014Interspeech1 citations
Semantic Scholar
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
Yue-Peng Hu, P. Ghahremani, Reza Aghajani, Mahesh Pasupuleti +1 more
20260 citations
Semantic Scholar
Mechanism for Ensuring Teacher’s Presence in Classroom Using Deep Learning
Rizwana Mahar, Ghulam Rasool Memon, T. Niemi-Laitinen, J. Saastamoinen +39 more
2020Gyancity Journal of Electronics and Computer Science0 citations Open access
Semantic Scholar
Learning Feature Representation for Automatic Speech Recognition
P. Ghahremani
20190 citations
Semantic Scholar
RÉSEAU NEURONAL PROFOND À AUTOSTABILISATION
James G. Droppo, P. Ghahremani, Avner May
20170 citations
Semantic Scholar
Self-Stabilized Deep Neural Net Poster
J. Droppo, P. Ghahremani
20160 citations
Semantic Scholar
A PRELIMINARY STUDY ON ASSOCIATED LEARNING FOR ASR
Pin-JuiKu, P. S. Nidadavolu, Brian King, P. Ghahremani +1 more
0 citations
Semantic Scholar