Kshitiz Kumar - RankMe

40 papers A 11C 2Misc 14Journal 5Unranked 6

Year	Rank	Type	Title / Venue / Authors
2024	—	`conf`	3D YOLO-SM: End-to-End Approach for Real-time Traffic Light Detection and Recognition in Complex Scenarios. VTC Fall Kshitiz Kumar, D. Santhosh Reddy, P. Rajalakshmi
2024	—	`conf`	Towards Real-Time Traffic Sign Recognition in Diverse Weather Conditions Through Adaptive Feature Learning. ITSC Kshitiz Kumar, D. Santhosh Reddy, P. Rajalakshmi
2023	J	`jnl`	Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss. CoRR Mohammad Soleymanpour, Mahmoud Al Ismail, Fahimeh Bahmaninezhad, Kshitiz Kumar, Jian Wu
2022	J	`jnl`	Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, And Pretraining: An Ablation Study. CoRR Daniel Tompkins, Kshitiz Kumar, Jian Wu
2022	Misc	`conf`	Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, and Pretraining: an Ablation Study. ICASSP Daniel Tompkins, Kshitiz Kumar, Jian Wu
2021	Misc	`conf`	Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts. ICASSP Amit Das, Kshitiz Kumar, Jian Wu
2021	A	`conf`	Sequence-Level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models. Interspeech Amber Afshan, Kshitiz Kumar, Jian Wu
2021	J	`jnl`	Sequence-level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models. CoRR Amber Afshan, Kshitiz Kumar, Jian Wu
2020	A	`conf`	1-D Row-Convolution LSTM: Fast Streaming ASR at Accuracy Parity with LC-BLSTM. INTERSPEECH Kshitiz Kumar, Chaojun Liu, Yifan Gong, Jian Wu
2020	A	`conf`	Bandpass Noise Generation and Augmentation for Unified ASR. INTERSPEECH Kshitiz Kumar, Bo Ren, Yifan Gong, Jian Wu
2020	A	`conf`	Fast and Slow Acoustic Model. INTERSPEECH Kshitiz Kumar, Emilian Stoimenov, Hosam Khalil, Jian Wu
2020	A	`conf`	Transfer Learning Approaches for Streaming End-to-End Speech Recognition System. INTERSPEECH Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li
2020	J	`jnl`	Transfer Learning Approaches for Streaming End-to-End Speech Recognition System. CoRR Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li
2019	J	`jnl`	Speaker Adaptation for End-to-End CTC Models. CoRR Ke Li, Jinyu Li, Yong Zhao, Kshitiz Kumar, Yifan Gong
2019	Misc	`conf`	Static and Dynamic State Predictions for Acoustic Model Combination. ICASSP Kshitiz Kumar, Yifan Gong
2019	Misc	`conf`	Word Characters and Phone Pronunciation Embedding for ASR Confidence Classifier. ICASSP Kshitiz Kumar, Tasos Anastasakos, Yifan Gong
2018	C	`conf`	A Comparative Study of Spatial Speech Separation Techniques to Improve Speech Recognition. ISNN Xinhui Zhou, Chiman Kwan, Bulent Ayhan, Chanwoo Kim, Kshitiz Kumar, Richard M. Stern
2018	—	`conf`	Speaker Adaptation for End-to-End CTC Models. SLT Ke Li, Jinyu Li, Yong Zhao, Kshitiz Kumar, Yifan Gong
2017	—	`ch.`	Challenges in and Solutions to Deep Learning Network Acoustic Modeling in Speech Recognition Products at Microsoft. New Era for Robust Speech Recognition, Exploiting Deep Learning Yifan Gong, Yan Huang, Kshitiz Kumar, Jinyu Li, Chaojun Liu, Guoli Ye, Shi-Xiong Zhang, Yong Zhao, Rui Zhao
2017	Misc	`conf`	Extended low-rank plus diagonal adaptation for deep and recurrent neural networks. ICASSP Yong Zhao, Jinyu Li, Kshitiz Kumar, Yifan Gong
2016	Misc	`conf`	Investigations on speaker adaptation of LSTM RNN models for speech recognition. ICASSP Chaojun Liu, Yongqiang Wang, Kshitiz Kumar, Yifan Gong
2016	Misc	`conf`	Non-negative intermediate-layer DNN adaptation for a 10-KB speaker adaptation profile. ICASSP Kshitiz Kumar, Chaojun Liu, Yifan Gong
2015	A	`conf`	Confidence-features and confidence-scores for ASR applications in arbitration and DNN speaker adaptation. INTERSPEECH Kshitiz Kumar, Ziad Al Bawab, Yong Zhao, Chaojun Liu, Benoît Dumoulin, Yifan Gong
2015	A	`conf`	Delta-melspectra features for noise robustness to DNN-based ASR systems. INTERSPEECH Kshitiz Kumar, Chaojun Liu, Yifan Gong
2015	A	`conf`	Intermediate-layer DNN adaptation for offline and session-based iterative speaker adaptation. INTERSPEECH Kshitiz Kumar, Chaojun Liu, Kaisheng Yao, Yifan Gong
2014	A	`conf`	Normalization of ASR confidence classifier scores via confidence mapping. INTERSPEECH Kshitiz Kumar, Chaojun Liu, Yifan Gong
2013	Misc	`conf`	Predicting speech recognition confidence using deep learning with word identity and score features. ICASSP Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng
2011	—	`—`	A Spectro-Temporal Framework for Compensation of Reverberation for Speech Recognition. Kshitiz Kumar
2011	Misc	`conf`	An iterative least-squares technique for dereverberation. ICASSP Kshitiz Kumar, Bhiksha Raj, Rita Singh, Richard M. Stern
2011	Misc	`conf`	Binaural sound source separation motivated by auditory processing. ICASSP Chanwoo Kim, Kshitiz Kumar, Richard M. Stern
2011	Misc	`conf`	Delta-spectral cepstral coefficients for robust speech recognition. ICASSP Kshitiz Kumar, Chanwoo Kim, Richard M. Stern
2011	Misc	`conf`	Gammatone sub-band magnitude-domain dereverberation for ASR. ICASSP Kshitiz Kumar, Rita Singh, Bhiksha Raj, Richard M. Stern
2010	Misc	`conf`	Maximum-likelihood-based cepstral inverse filtering for blind speech dereverberation. ICASSP Kshitiz Kumar, Richard M. Stern
2009	—	`conf`	Audio-visual speech synchronization detection using a bimodal linear prediction model. CVPR Workshops Kshitiz Kumar, Jirí Navrátil, Etienne Marcheret, Vit Libal, Ganesh N. Ramaswamy, Gerasimos Potamianos
2009	A	`conf`	Robust audio-visual speech synchrony detection by generalized bimodal linear prediction. INTERSPEECH Kshitiz Kumar, Jirí Navrátil, Etienne Marcheret, Vit Libal, Gerasimos Potamianos
2009	C	`conf`	Robust speech recognition using a Small Power Boosting algorithm. ASRU Chanwoo Kim, Kshitiz Kumar, Richard M. Stern
2009	A	`conf`	Signal separation for robust speech recognition based on phase difference information obtained in the frequency domain. INTERSPEECH Chanwoo Kim, Kshitiz Kumar, Bhiksha Raj, Richard M. Stern
2008	Misc	`conf`	Environment-invariant compensation for reverberation using linear post-filtering for minimum distortion. ICASSP Kshitiz Kumar, Richard M. Stern
2008	—	`conf`	Noise robust speaker identification using Bhattacharyya distance in adapted Gaussian models space. EUSIPCO Kshitiz Kumar, Qi Wu, Yiming Wang, Marios Savvides
2007	—	`conf`	Profile View Lip Reading. ICASSP (4) Kshitiz Kumar, Tsuhan Chen, Richard M. Stern