Следене
Nithin Rao Koluguri
Nithin Rao Koluguri
Потвърден имейл адрес: nvidia.com - Начална страница
Заглавие
Позовавания
Позовавания
Година
Titanet: Neural model for speaker representation with 1d depth-wise separable convolutions and global context
NR Koluguri, T Park, B Ginsburg
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
692022
SpeakerNet: 1D depth-wise separable convolutional network for text-independent speaker recognition and verification
NR Koluguri, J Li, V Lavrukhin, B Ginsburg
arXiv preprint arXiv:2010.12653, 2020
412020
Comparison of Speech Tasks and Recording Devices for Voice Based Automatic Classification of Healthy Subjects and Patients with Amyotrophic Lateral Sclerosis.
BN Suhas, D Patel, NR Koluguri, Y Belur, P Reddy, A Nalini, R Yadav, ...
INTERSPEECH, 4564-4568, 2019
242019
Meta-learning for robust child-adult classification from speech
NR Koluguri, M Kumar, SH Kim, C Lord, S Narayanan
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
202020
Spectrogram enhancement using multiple window Savitzky-Golay (MWSG) filter for robust bird sound detection
NR Koluguri, GN Meenakshi, PK Ghosh
IEEE/ACM Transactions on Audio, Speech, and Language Processing 25 (6), 1183 …, 2017
192017
Fast conformer with linearly scalable attention for efficient speech recognition
D Rekesh, NR Koluguri, S Kriman, S Majumdar, V Noroozi, H Huang, ...
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-8, 2023
162023
Multi-scale speaker diarization with dynamic scale weighting
TJ Park, NR Koluguri, J Balam, B Ginsburg
arXiv preprint arXiv:2203.15974, 2022
142022
Enhancing speaker diarization with large language models: A contextual beam search approach
TJ Park, K Dhawan, N Koluguri, J Balam
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
42024
Ambernet: A compact end-to-end model for spoken language identification
F Jia, NR Koluguri, J Balam, B Ginsburg
arXiv preprint arXiv:2210.15781, 2022
32022
Property-Aware Multi-Speaker Data Simulation: A Probabilistic Modelling Technique for Synthetic Data Generation
TJ Park, H Huang, C Hooper, N Koluguri, K Dhawan, A Jukic, J Balam, ...
arXiv preprint arXiv:2310.12371, 2023
22023
Investigating End-to-End ASR Architectures for Long Form Audio Transcription
NR Koluguri, S Kriman, G Zelenfroind, S Majumdar, D Rekesh, V Noroozi, ...
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
12024
The CHiME-7 Challenge: System Description and Performance of NeMo Team's DASR System
TJ Park, H Huang, A Jukic, K Dhawan, KC Puvvada, N Koluguri, N Karpov, ...
arXiv preprint arXiv:2310.12378, 2023
12023
Discrete Audio Representation as an Alternative to Mel-Spectrograms for Speaker and Speech Recognition
KC Puvvada, NR Koluguri, K Dhawan, J Balam, B Ginsburg
ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024
2024
SPEAKER IDENTIFICATION, VERIFICATION, AND DIARIZATION USING NEURAL NETWORKS FOR CONVERSATIONAL AI SYSTEMS AND APPLICATIONS
NR Koluguri, T Park, B Ginsburg
US Patent App. 17/962,248, 2024
2024
Open Automatic Speech Recognition Leaderboard
SHFTNNMTSBT Srivastav, Vaibhav and Majumdar, Somshubra and Koluguri, Nithin ...
https://huggingface.co/spaces/huggingface.co/spaces/open-asr-leaderboard …, 2023
2023
NeMo Open Source Speaker Diarization System.
T Park, NR Koluguri, F Jia, J Balam, B Ginsburg
INTERSPEECH, 853-854, 2022
2022
Prototypical Networks for Robust Automatic Child-Adult Classification from Speech
M Kumar, N Koluguri, SH Kim, C Lord, S Narayanan
INSAR 2020 Virtual Meeting, 0
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–17