Follow
Desh Raj
Desh Raj
Center for Language and Speech Processing, Johns Hopkins University
Verified email at cs.jhu.edu - Homepage
Title
Cited by
Cited by
Year
CHiME-6 challenge: Tackling multispeaker speech recognition for unsegmented recordings
S Watanabe, M Mandel, J Barker, E Vincent, A Arora, X Chang, ...
arXiv preprint arXiv:2004.09249, 2020
1692020
Probing the information encoded in x-vectors
D Raj, D Snyder, D Povey, S Khudanpur
2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2019
732019
Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text
D Raj, S Sahu, A Anand
Proceedings of the 21st conference on computational natural language …, 2017
372017
Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis
D Raj, P Denisov, Z Chen, H Erdogan, Z Huang, M He, S Watanabe, J Du, ...
2021 IEEE spoken language technology workshop (SLT), 897-904, 2021
362021
Dover-lap: A method for combining overlap-aware diarization outputs
D Raj, LP Garcia-Perera, Z Huang, S Watanabe, D Povey, A Stolcke, ...
2021 IEEE Spoken Language Technology Workshop (SLT), 881-888, 2021
322021
Sequential multi-frame neural beamforming for speech separation and enhancement
ZQ Wang, H Erdogan, S Wisdom, K Wilson, D Raj, S Watanabe, Z Chen, ...
2021 IEEE Spoken Language Technology Workshop (SLT), 905-911, 2021
262021
The Hitachi-JHU DIHARD III system: Competitive end-to-end neural diarization and x-vector clustering systems combined by DOVER-Lap
S Horiguchi, N Yalta, P Garcia, Y Takashima, Y Xue, D Raj, Z Huang, ...
arXiv preprint arXiv:2102.01363, 2021
172021
Using ASR methods for OCR
A Arora, CC Chang, B Rekabdar, B BabaAli, D Povey, D Etter, D Raj, ...
2019 International Conference on Document Analysis and Recognition (ICDAR …, 2019
172019
Uncertain fuzzy self-organization based clustering: interval type-2 approach to adaptive resonance theory
S Majheed, A Gupta, D Raj, FCH Rhee
Information Sciences, 2017
17*2017
Multi-class spectral clustering with overlaps for speaker diarization
D Raj, Z Huang, S Khudanpur
2021 IEEE Spoken Language Technology Workshop (SLT), 582-589, 2021
112021
Target-speaker voice activity detection with improved i-vector estimation for unknown number of speaker
M He, D Raj, Z Huang, J Du, Z Chen, S Watanabe
arXiv preprint arXiv:2108.03342, 2021
92021
The JHU multi-microphone multi-speaker ASR system for the CHiME-6 challenge
A Arora, D Raj, AS Subramanian, K Li, B Ben-Yair, M Maciejewski, ...
arXiv preprint arXiv:2006.07898, 2020
92020
Analysis of Data Generated from Multidimensional Type-1 and Type-2 Fuzzy Membership Functions
D Raj, A Gupta, B Garg, K Tanna, FCH Rhee
IEEE Transactions on Fuzzy Systems, 0
9*
Continuous streaming multi-talker asr with dual-path transducers
D Raj, L Lu, Z Chen, Y Gaur, J Li
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
52022
Auxiliary loss function for target speech extraction and recognition with weak supervision based on speaker characteristics
K Zmolikova, M Delcroix, D Raj, S Watanabe, J Cernocký
Interspeech, 2021
42021
Injecting text and cross-lingual supervision in few-shot learning from self-supervised models
M Wiesner, D Raj, S Khudanpur
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
32022
Frustratingly easy noise-aware training of acoustic models
D Raj, J Villalba, D Povey, S Khudanpur
arXiv preprint arXiv:2011.02090, 2020
32020
Visual analysis and representations of type-2 fuzzy membership functions
D Raj, K Tanna, B Garg, FCH Rhee
IEEE International Conference on Fuzzy Systems, 550-554, 2016
32016
Reformulating DOVER-Lap label mapping as a graph partitioning problem
D Raj, S Khudanpur
arXiv preprint arXiv:2104.01954, 2021
12021
Training Hybrid Models on Noisy Transliterated Transcripts for Code-Switched Speech Recognition.
M Wiesner, M Sarma, A Arora, D Raj, D Gao, R Huang, S Preet, ...
Interspeech, 2906-2910, 2021
12021
The system can't perform the operation now. Try again later.
Articles 1–20