scispace - formally typeset
Search or ask a question
Institution

International Institute of Information Technology, Hyderabad

EducationHyderabad, India
About: International Institute of Information Technology, Hyderabad is a education organization based out in Hyderabad, India. It is known for research contribution in the topics: Authentication & Internet security. The organization has 2048 authors who have published 3677 publications receiving 45319 citations. The organization is also known as: IIIT Hyderabad & International Institute of Information Technology (IIIT).


Papers
More filters
Proceedings ArticleDOI
20 Aug 2017
TL;DR: The experimental results on ASVspoof 2017 dataset reveal that, SFF based representation is very effective in detecting replay attacks and the score level fusion of back end classifiers further improved the performance of the system which indicates that both classifiers capture complimentary information.
Abstract: The ASVspoof 2017 challenge is about the detection of replayed speech from human speech. The proposed system makes use of the fact that when the speech signals are replayed, they pass through multiple channels as opposed to original recordings. This channel information is typically embedded in low signal to noise ratio regions. A speech signal processing method with high spectro temporal resolution is required to extract robust features from such regions. The single frequency filtering (SFF) is one such technique, which we propose to use for replay attack detection. While SFF based feature representation was used at front-end, Gaussian mixture model and bi-directional long short-term memory models are investigated at the backend as classifiers. The experimental results on ASVspoof 2017 dataset reveal that, SFF based representation is very effective in detecting replay attacks. The score level fusion of back end classifiers further improved the performance of the system which indicates that both classifiers capture complimentary information.

56 citations

Proceedings Article
06 Jun 2019
TL;DR: This work proposes a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations and uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions.
Abstract: In order to integrate uncertainty estimates into deep time-series modelling, Kalman Filters (KFs) (Kalman et al., 1960) have been integrated with deep learning models, however, such approaches typically rely on approximate inference tech- niques such as variational inference which makes learning more complex and often less scalable due to approximation errors. We propose a new deep approach to Kalman filtering which can be learned directly in an end-to-end manner using backpropagation without additional approximations. Our approach uses a high-dimensional factorized latent state representation for which the Kalman updates simplify to scalar operations and thus avoids hard to backpropagate, computationally heavy and potentially unstable matrix inversions. Moreover, we use locally linear dynamic models to efficiently propagate the latent state to the next time step. The resulting network architecture, which we call Recurrent Kalman Network (RKN), can be used for any time-series data, similar to a LSTM (Hochreiter & Schmidhuber, 1997) but uses an explicit representation of uncertainty. As shown by our experiments, the RKN obtains much more accurate uncertainty estimates than an LSTM or Gated Recurrent Units (GRUs) (Cho et al., 2014) while also showing a slightly improved prediction performance and outperforms various recent generative models on an image imputation task.

56 citations

Journal ArticleDOI
TL;DR: In this article, a bag-of-words classifier was proposed to recognize first person actions in egocentric videos, which does not assume segmentation of hand/objects or recognizing object or hand pose.

56 citations

Proceedings ArticleDOI
12 May 2008
TL;DR: This paper investigates the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm and proposes the hierarchical estimation of phoneme posterior probabilities.
Abstract: In this paper, we investigate the significance of contextual information in a phoneme recognition system using the hidden Markov model - artificial neural network paradigm. Contextual information is probed at the feature level as well as at the output of the multilayered perceptron. At the feature level, we analyze and compare different methods to model sub-phonemic classes. To exploit the contextual information at the output of the multilayered perceptron, we propose the hierarchical estimation of phoneme posterior probabilities. The best phoneme (excluding silence) recognition accuracy of 73.4% on the TIMIT database is comparable to that of the state-of- the-art systems, but more emphasis is on analysis of the contextual information.

56 citations

Proceedings ArticleDOI
01 Jan 2018
TL;DR: A sequence- to-sequence deep learning model which trains end-to-end spelling correction techniques for resource-scarce languages and a comparative evaluation shows that the model is competitive with the existing spell checking and Correction techniques for Indic languages.
Abstract: Spelling correction is a well-known task in Natural Language Processing (NLP). Automatic spelling correction is important for many NLP applications like web search engines, text summarization, sentiment analysis etc. Most approaches use parallel data of noisy and correct word mappings from different sources as training data for automatic spelling correction. Indic languages are resource-scarce and do not have such parallel data due to low volume of queries and non-existence of such prior implementations. In this paper, we show how to build an automatic spelling corrector for resource-scarce languages. We propose a sequence-to-sequence deep learning model which trains end-to-end. We perform experiments on synthetic datasets created for Indic languages, Hindi and Telugu, by incorporating the spelling mistakes committed at character level. A comparative evaluation shows that our model is competitive with the existing spell checking and correction techniques for Indic languages.

56 citations


Authors

Showing all 2066 results

NameH-indexPapersCitations
Ravi Shankar6667219326
Joakim Nivre6129517203
Aravind K. Joshi5924916417
Ashok Kumar Das562789166
Malcolm F. White5517210762
B. Yegnanarayana5434012861
Ram Bilas Pachori481828140
C. V. Jawahar454799582
Saurabh Garg402066738
Himanshu Thapliyal362013992
Monika Sharma362384412
Ponnurangam Kumaraguru332696849
Abhijit Mitra332407795
Ramanathan Sowdhamini332564458
Helmut Schiessel321173527
Network Information
Related Institutions (5)
Microsoft
86.9K papers, 4.1M citations

90% related

Facebook
10.9K papers, 570.1K citations

89% related

Google
39.8K papers, 2.1M citations

89% related

Carnegie Mellon University
104.3K papers, 5.9M citations

87% related

Performance
Metrics
No. of papers from the Institution in previous years
YearPapers
202310
202229
2021373
2020440
2019367
2018364