• Publications
  • Influence
Bidirectional recurrent neural networks
In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent network (BRNN). Expand
  • 3,827
  • 589
  • PDF
Efficient vector quantization of LPC parameters at 24 bits/frame
  • K. Paliwal, B. Atal
  • Mathematics, Computer Science
  • IEEE Trans. Speech Audio Process.
  • 1993
A split vector quantizer can quantize LPC information in 24 bits/frame with an average spectral distortion of 1 dB and less than 2% of the frames having spectral distortion. Expand
  • 469
  • 50
  • PDF
Efficient vector quantization of LPC parameters at 24 bits/frame
Linear prediction coding (LPC) parameters are widely used in various speech processing applications for representing the spectral envelope information of speech. For low‐bit‐rate speech codingExpand
  • 252
  • 37
Speech Coding and Synthesis
An introduction to speech coding, W. Paliwal and W. Kroon a robust algorithm for pitch tracking (RAPT), D. McAulay and T. Kubin an approach to text-to-speech synthesis, R. Hedelin et al theory for transmission of vector quantization data, P. Kleijn evaluation of speech coders, J.-H. Expand
  • 604
  • 36
Identity verification using speech and face information
This article first provides an overview of important concept s in the field of information fusion, followed by a review of milestones in audio-visual person identification and verifi cation. Expand
  • 170
  • 19
  • PDF
Improving prediction of secondary structure, local backbone angles, and solvent accessible surface area of proteins by iterative deep learning
Direct prediction of protein structure from sequence is a challenging problem. An effective approach is to break it up into independent sub-problems. These sub-problems such as prediction of proteinExpand
  • 240
  • 18
  • PDF
Fast features for face authentication under illumination direction changes
In this letter we propose a facial feature extraction technique which utilizes polynomial coefficients derived from 2D Discrete Cosine Transform (DCT) coefficients obtained from horizontally and vertically neighbouring blocks. Expand
  • 178
  • 18
  • PDF
Capturing non‐local interactions by long short‐term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and
We showed that the application of LSTM‐BRNN to the prediction of protein structural properties makes the most significant improvement for residues with the most long‐range contacts (|i‐j| >19) over a previous window‐based, deep‐learning method SPIDER2. Expand
  • 157
  • 16
  • PDF
A speech enhancement method based on Kalman filtering
  • K. Paliwal, A. Basu
  • Computer Science
  • ICASSP '87. IEEE International Conference on…
  • 6 April 1987
In this paper, the problem of speech enhancement when only corrupted speech signal is available for processing is considered. Expand
  • 309
  • 15
  • PDF
Automatic Speech and Speaker Recognition: Advanced Topics
Automatic Speech and Speaker Recognition: Advanced Topics groups together in a single volume a number of important topics on speech and speaker recognition, topics which are of fundamental importance, but not yet covered in detail in existing textbooks. Expand
  • 256
  • 14