Zobrazeno 1 - 10
of 15
pro vyhledávání: '"Ruchir Travadi"'
Autor:
Tracy Tuplin, Shrikanth S. Narayanan, Krishna Somandepalli, Fernando Rivera, Ruchir Travadi, Raghuveer Peri, Rajat Hebbar
Publikováno v:
CBMI
International organizations such as the United Nations drive policies that impact our everyday lives. Diverse representation of people and ideas in the decision making process of such bodies is critical to ensure that the policies work for everyone.
Autor:
Ruchir Travadi, Shrikanth S. Narayanan
Publikováno v:
IEEE Signal Processing Letters. 26:893-897
The total variability model (TVM) has been extensively used as a tool to obtain a vector representation of the sources of variability present in a signal. However, recent studies have shown that embeddings derived from a deep neural network (DNN) arc
Autor:
Shrikanth S. Narayanan, Ruchir Travadi
Publikováno v:
Computer Speech & Language. 53:43-64
A number of audio signal processing applications characterize different properties of the source underlying an audio signal by analyzing the distribution of a sequence of feature vectors obtained from the signal. The Total Variability Model has been
The Listen, Attend and Spell (LAS) model and other attention-based automatic speech recognition (ASR) models have known limitations when operated in a fully online mode. In this paper, we analyze the online operation of LAS models to demonstrate that
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f28137a24cde313f14be16742b858222
Autor:
Raghuveer Peri, Monisankha Pal, Tae Jin Park, Panayiotis G. Georgiou, Naveen Kumar, Shrikanth S. Narayanan, Ruchir Travadi, Arindam Jati
Publikováno v:
INTERSPEECH
Publikováno v:
ICASSP
We propose a semi-supervised learning method to improve classification performance in scenarios with limited labeled data. We employ adaptation strategies such as entropy-filtering and self-training, and show that our method achieves up to 17.2% rela
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 23:1118-1129
A critical challenge to automatic language identification (LID) is achieving accurate performance with the shortest possible speech segment in a rapid fashion. The accuracy to correctly identify the spoken language is highly sensitive to the duration
Autor:
Boliang Zhang, Colin Vaz, Heng Ji, Lukas Burget, Di Lu, Ying Lin, Martin Karafiat, Shrikanth S. Narayanan, Kevin Knight, Mark Hasegawa-Johnson, Jonathan May, Michael Pust, Ondřej Glembek, Pavlos Papadopoulos, Murali Karthick Baskar, Nima Pourdamghani, Ruchir Travadi, Nikolaos Malandrakis, Xiaoman Pan, Ulf Hermjakob
Publikováno v:
INTERSPEECH
Autor:
Shrikanth S. Narayanan, Ruchir Travadi
Publikováno v:
INTERSPEECH
Publikováno v:
INTERSPEECH