Jithendar Anumula
University of Zurich
15 Papers
61 Citations
Jithendar Anumula is an academic researcher from University of Zurich. The author has contributed to research in topics: Recurrent neural network & Vanishing gradient problem. The author has an hindex of 6, co-authored 15 publications.
Chat about Author
Papers
Feature representations for neuromorphic audio spike streams
TL;DR: This work investigates the effectiveness of synchronous and asynchronous frame-based features generated using spike count and constant event binning in combination with the use of a recurrent neural network for solving a classification task using N-TIDIGITS18 dataset and proposes a new pre-processing method which applies an exponential kernel on the output cochlea spikes so that the interspike timing information is better preserved.
•Posted Content
Overcoming the vanishing gradient problem in plain recurrent networks
TL;DR: A novel network called the Recurrent Identity Network (RIN) is proposed which allows a plain recurrent network to overcome the vanishing gradient problem while training very deep models without the use of gates.
Multi-channel attention for end-to-end speech recognition
Stefan Braun,Daniel Neil,Jithendar Anumula,Enea Ceolini,Shih-Chii Liu +4 more
- 02 Sep 2018
TL;DR: This work proposes a sensory attention mechanism that is invariant to the channel ordering and only increases the overall parameter count by 0.09%, and demonstrates that even without re-training, this attention-equipped end-to-end model is able to deal with arbitrary numbers of input channels during inference.
Event-driven Pipeline for Low-latency Low-compute Keyword Spotting and Speaker Verification System
Enea Ceolini,Jithendar Anumula,Stefan Braun,Shih-Chii Liu +3 more
- 12 May 2019
TL;DR: Evaluation on a self-recorded event dataset based on TIDIGITS shows accuracies of over 93% and 88% on KWS and SV respectively, with minimum system latency of 5 ms on a limited resource device.
20
Attention-driven Multi-sensor Selection
Stefan Braun,Daniel Neil,Jithendar Anumula,Enea Ceolini,Shih-Chii Liu +4 more
- 14 Jul 2019
TL;DR: A sensor transformation attention network (STAN) that embeds a sensory attention mechanism to dynamically weigh and combine individual input sensors based on their task-relevant information is reported on.