Follow
Prashanth Gurunath Shivakumar
Prashanth Gurunath Shivakumar
Verified email at usc.edu
Title
Cited by
Cited by
Year
Transfer learning from adult to children for speech recognition: Evaluation, analysis and recommendations
PG Shivakumar, P Georgiou
Computer speech & language 63, 101077, 2020
1432020
Multimodal and multiresolution depression detection from speech and facial landmark features
M Nasir, A Jati, PG Shivakumar, S Nallan Chakravarthula, P Georgiou
Proceedings of the 6th international workshop on audio/visual emotion …, 2016
1422016
Improving speech recognition for children using acoustic adaptation and pronunciation modeling.
PG Shivakumar, A Potamianos, S Lee, SS Narayanan
WOCCI, 15-19, 2014
872014
Perception optimized deep denoising autoencoders for speech enhancement.
PG Shivakumar, PG Georgiou
Interspeech, 3743-3747, 2016
562016
End-to-end neural systems for automatic children speech recognition: An empirical study
PG Shivakumar, S Narayanan
Computer Speech & Language 72, 101289, 2022
392022
Learning from past mistakes: improving automatic speech recognition output via noisy-clean phrase context modeling
PG Shivakumar, H Li, K Knight, P Georgiou
APSIPA Transactions on Signal and Information Processing 8, e8, 2019
312019
Spoken Language Intent Detection Using Confusion2Vec
PG Shivakumar, M Yang, P Georgiou
Proc. Interspeech 2019, 819--823, 2019
302019
Confusion2vec: Towards enriching vector space word representations with representational ambiguities
PG Shivakumar, P Georgiou
PeerJ Computer Science 5, e195, 2019
242019
Simplified and supervised i-vector modeling for speaker age regression
PG Shivakumar, M Li, V Dhandhania, SS Narayanan
2014 IEEE International Conference on Acoustics, Speech and Signal …, 2014
212014
Low-rank adaptation of large language model rescoring for parameter-efficient speech recognition
Y Yu, CHH Yang, J Kolehmainen, PG Shivakumar, Y Gu, SRR Ren, Q Luo, ...
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023
142023
Multimodal Fusion of Multirate Acoustic, Prosodic, and Lexical Speaker Characteristics for Native Language Identification.
PG Shivakumar, SN Chakravarthula, PG Georgiou
INTERSPEECH, 2408-2412, 2016
132016
Scaling laws for discriminative speech recognition rescoring models
Y Gu, PG Shivakumar, J Kolehmainen, A Gandhe, A Rastrow, I Bulyko
arXiv preprint arXiv:2306.15815, 2023
52023
Incremental online spoken language understanding
PG Shivakumar, N Kumar, P Georgiou, S Narayanan
arXiv preprint arXiv:1910.10287, 2019
42019
Paralinguistics-enhanced large language modeling of spoken dialogue
GT Lin, PG Shivakumar, A Gandhe, CHH Yang, Y Gu, S Ghosh, A Stolcke, ...
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
32024
Rnn based incremental online spoken language understanding
PG Shivakumar, N Kumar, P Georgiou, S Narayanan
2021 IEEE Spoken Language Technology Workshop (SLT), 989-996, 2021
32021
Behavior gated language models
PG Shivakumar, SY Tseng, P Georgiou, S Narayanan
arXiv preprint arXiv:1909.00107, 2019
32019
Distillation strategies for discriminative speech recognition rescoring
PG Shivakumar, J Kolehmainen, Y Gu, A Gandhe, A Rastrow, I Bulyko
arXiv preprint arXiv:2306.09452, 2023
22023
Confusion2Vec 2.0: Enriching ambiguous spoken language representations with subwords
P Gurunath Shivakumar, P Georgiou, S Narayanan
Plos one 17 (3), e0264488, 2022
22022
Towards ASR robust spoken language understanding through in-context learning with word confusion networks
K Everson, Y Gu, H Yang, PG Shivakumar, GT Lin, J Kolehmainen, ...
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
12024
Personalization for bert-based discriminative speech recognition rescoring
J Kolehmainen, Y Gu, A Gourav, PG Shivakumar, A Gandhe, A Rastrow, ...
arXiv preprint arXiv:2307.06832, 2023
12023
The system can't perform the operation now. Try again later.
Articles 1–20