Kshitiz Kumar

According to our database, Kshitiz Kumar authored at least 35 papers between 2007 and 2024.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2024

3D YOLO-SM: End-to-End Approach for Real-time Traffic Light Detection and Recognition in Complex Scenarios.

Kshitiz Kumar, D. Santhosh Reddy, P. Rajalakshmi

Proceedings of the 100th IEEE Vehicular Technology Conference, 2024

2023

Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss.

Mohammad Soleymanpour, Mahmoud Al Ismail, Fahimeh Bahmaninezhad, Kshitiz Kumar, Jian Wu

CoRR, 2023

2022

Maximizing Audio Event Detection Model Performance on Small Datasets Through Knowledge Transfer, Data Augmentation, and Pretraining: an Ablation Study.

Daniel Tompkins, Kshitiz Kumar, Jian Wu

Proceedings of the IEEE International Conference on Acoustics, 2022

2021

Sequence-Level Confidence Classifier for ASR Utterance Accuracy and Application to Acoustic Models.

Amber Afshan, Kshitiz Kumar, Jian Wu

Proceedings of the 22nd Annual Conference of the International Speech Communication Association, Interspeech 2021, Brno, Czechia, August 30, 2021

Multi-Dialect Speech Recognition in English Using Attention on Ensemble of Experts.

Amit Das, Kshitiz Kumar, Jian Wu

Proceedings of the IEEE International Conference on Acoustics, 2021

2020

Fast and Slow Acoustic Model.

Kshitiz Kumar, Emilian Stoimenov, Hosam Khalil, Jian Wu

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Bandpass Noise Generation and Augmentation for Unified ASR.

Kshitiz Kumar, Bo Ren, Yifan Gong, Jian Wu

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

1-D Row-Convolution LSTM: Fast Streaming ASR at Accuracy Parity with LC-BLSTM.

Kshitiz Kumar, Chaojun Liu, Yifan Gong, Jian Wu

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

Transfer Learning Approaches for Streaming End-to-End Speech Recognition System.

Vikas Joshi, Rui Zhao, Rupesh R. Mehta, Kshitiz Kumar, Jinyu Li

Proceedings of the 21st Annual Conference of the International Speech Communication Association, 2020

2019

Static and Dynamic State Predictions for Acoustic Model Combination.

Kshitiz Kumar, Yifan Gong

Proceedings of the IEEE International Conference on Acoustics, 2019

Word Characters and Phone Pronunciation Embedding for ASR Confidence Classifier.

Kshitiz Kumar, Tasos Anastasakos, Yifan Gong

Proceedings of the IEEE International Conference on Acoustics, 2019

2018

Speaker Adaptation for End-to-End CTC Models.

Ke Li, Jinyu Li, Yong Zhao, Kshitiz Kumar, Yifan Gong

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

A Comparative Study of Spatial Speech Separation Techniques to Improve Speech Recognition.

Xinhui Zhou, Chiman Kwan, Bulent Ayhan, Chanwoo Kim, Kshitiz Kumar, Richard M. Stern

Proceedings of the Advances in Neural Networks - ISNN 2018, 2018

2017

Extended low-rank plus diagonal adaptation for deep and recurrent neural networks.

Yong Zhao, Jinyu Li, Kshitiz Kumar, Yifan Gong

Proceedings of the 2017 IEEE International Conference on Acoustics, 2017

Challenges in and Solutions to Deep Learning Network Acoustic Modeling in Speech Recognition Products at Microsoft.

Yifan Gong, Yan Huang, Kshitiz Kumar, Jinyu Li, Chaojun Liu, Guoli Ye, Shi-Xiong Zhang, Yong Zhao, Rui Zhao

Proceedings of the New Era for Robust Speech Recognition, Exploiting Deep Learning., 2017

2016

Investigations on speaker adaptation of LSTM RNN models for speech recognition.

Chaojun Liu, Yongqiang Wang, Kshitiz Kumar, Yifan Gong

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

Non-negative intermediate-layer DNN adaptation for a 10-KB speaker adaptation profile.

Kshitiz Kumar, Chaojun Liu, Yifan Gong

Proceedings of the 2016 IEEE International Conference on Acoustics, 2016

2015

Intermediate-layer DNN adaptation for offline and session-based iterative speaker adaptation.

Kshitiz Kumar, Chaojun Liu, Kaisheng Yao, Yifan Gong

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Delta-melspectra features for noise robustness to DNN-based ASR systems.

Kshitiz Kumar, Chaojun Liu, Yifan Gong

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Confidence-features and confidence-scores for ASR applications in arbitration and DNN speaker adaptation.

Kshitiz Kumar, Ziad Al Bawab, Yong Zhao, Chaojun Liu, Benoît Dumoulin, Yifan Gong

Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

2014

Normalization of ASR confidence classifier scores via confidence mapping.

Kshitiz Kumar, Chaojun Liu, Yifan Gong

Proceedings of the 15th Annual Conference of the International Speech Communication Association, 2014

2013

Predicting speech recognition confidence using deep learning with word identity and score features.

Po-Sen Huang, Kshitiz Kumar, Chaojun Liu, Yifan Gong, Li Deng

Proceedings of the IEEE International Conference on Acoustics, 2013

2011

A Spectro-Temporal Framework for Compensation of Reverberation for Speech Recognition.

Kshitiz Kumar

PhD thesis, 2011

Gammatone sub-band magnitude-domain dereverberation for ASR.

Kshitiz Kumar, Rita Singh, Bhiksha Raj, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2011

An iterative least-squares technique for dereverberation.

Kshitiz Kumar, Bhiksha Raj, Rita Singh, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2011

Delta-spectral cepstral coefficients for robust speech recognition.

Kshitiz Kumar, Chanwoo Kim, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2011

Binaural sound source separation motivated by auditory processing.

Chanwoo Kim, Kshitiz Kumar, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2011

2010

Maximum-likelihood-based cepstral inverse filtering for blind speech dereverberation.

Kshitiz Kumar, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2010

2009

Robust audio-visual speech synchrony detection by generalized bimodal linear prediction.

Kshitiz Kumar, Jirí Navrátil, Etienne Marcheret, Vit Libal, Gerasimos Potamianos

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Signal separation for robust speech recognition based on phase difference information obtained in the frequency domain.

Chanwoo Kim, Kshitiz Kumar, Bhiksha Raj, Richard M. Stern

Proceedings of the 10th Annual Conference of the International Speech Communication Association, 2009

Audio-visual speech synchronization detection using a bimodal linear prediction model.

Kshitiz Kumar, Jirí Navrátil, Etienne Marcheret, Vit Libal, Ganesh N. Ramaswamy, Gerasimos Potamianos

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2009

Robust speech recognition using a Small Power Boosting algorithm.

Chanwoo Kim, Kshitiz Kumar, Richard M. Stern

Proceedings of the 2009 IEEE Workshop on Automatic Speech Recognition & Understanding, 2009

2008

Environment-invariant compensation for reverberation using linear post-filtering for minimum distortion.

Kshitiz Kumar, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2008

Noise robust speaker identification using Bhattacharyya distance in adapted Gaussian models space.

Kshitiz Kumar, Qi Wu, Yiming Wang, Marios Savvides

Proceedings of the 2008 16th European Signal Processing Conference, 2008

2007

Profile View Lip Reading.

Kshitiz Kumar, Tsuhan Chen, Richard M. Stern

Proceedings of the IEEE International Conference on Acoustics, 2007