Showing results for Arun Narayanan
Search instead for Arun Naranayan
User profiles for Arun Narayanan
Arun NarayananSenior Staff Research Scientist at Google Deepmind Verified email at google.com Cited by 5572 |
Ideal ratio mask estimation using deep neural networks for robust speech recognition
A Narayanan, DL Wang - 2013 IEEE international conference …, 2013 - ieeexplore.ieee.org
We propose a feature enhancement algorithm to improve robust automatic speech recognition
(ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel frequency …
(ASR). The algorithm estimates a smoothed ideal ratio mask (IRM) in the Mel frequency …
On training targets for supervised speech separation
Formulation of speech separation as a supervised learning problem has shown considerable
promise. In its simplest form, a supervised learning algorithm, typically a deep neural …
promise. In its simplest form, a supervised learning algorithm, typically a deep neural …
Investigation of speech separation as a front-end for noise robust speech recognition
A Narayanan, DL Wang - IEEE/ACM Transactions on Audio …, 2014 - ieeexplore.ieee.org
Recently, supervised classification has been shown to work well for the task of speech
separation. We perform an in-depth evaluation of such techniques as a front-end for noise-robust …
separation. We perform an in-depth evaluation of such techniques as a front-end for noise-robust …
Multichannel signal processing with deep neural networks for automatic speech recognition
Multichannel automatic speech recognition (ASR) systems commonly separate speech
enhancement, including localization, beamforming, and postfiltering, from acoustic modeling. In …
enhancement, including localization, beamforming, and postfiltering, from acoustic modeling. In …
[PDF][PDF] Generation of Large-Scale Simulated Utterances in Virtual Rooms to Train Deep-Neural Networks for Far-Field Speech Recognition in Google Home.
We describe the structure and application of an acoustic room simulator to generate large-scale
simulated data for training deep neural networks for far-field speech recognition. The …
simulated data for training deep neural networks for far-field speech recognition. The …
A streaming on-device end-to-end model surpassing server-side conventional model quality and latency
Thus far, end-to-end (E2E) models have not been shown to outperform state-of-the-art
conventional models with respect to both quality, ie, word error rate (WER), and latency, ie, the …
conventional models with respect to both quality, ie, word error rate (WER), and latency, ie, the …
[PDF][PDF] Acoustic Modeling for Google Home.
This paper describes the technical and system building advances made to the Google
Home multichannel speech recognition system, which was launched in November 2016. …
Home multichannel speech recognition system, which was launched in November 2016. …
Effect of coconut oil in plaque related gingivitis—A preliminary report
…, P Sreenivasan, A Narayanan - Nigerian Medical …, 2015 - journals.lww.com
Background: Oil pulling or oil swishing therapy is a traditional procedure in which the practitioners
rinse or swish oil in their mouth. It is supposed to cure oral and systemic diseases but …
rinse or swish oil in their mouth. It is supposed to cure oral and systemic diseases but …
From audio to semantics: Approaches to end-to-end spoken language understanding
Conventional spoken language understanding systems consist of two main components: an
automatic speech recognition module that converts audio to a transcript, and a natural …
automatic speech recognition module that converts audio to a transcript, and a natural …
Recognizing long-form speech using streaming end-to-end models
All-neural end-to-end (E2E) automatic speech recognition (ASR) systems that use a single
neural network to transduce audio to word sequences have been shown to achieve state-of-…
neural network to transduce audio to word sequences have been shown to achieve state-of-…