Showing results for Arun Narayanan

Search instead for Arun Naranayan

User profiles for Arun Narayanan

Arun Narayanan

Senior 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 …

On training targets for supervised speech separation

Y Wang, A Narayanan, DL Wang - IEEE/ACM transactions on …, 2014 - ieeexplore.ieee.org
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 …

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 …

Multichannel signal processing with deep neural networks for automatic speech recognition

…, KW Wilson, B Li, A Narayanan… - … on Audio, Speech …, 2017 - ieeexplore.ieee.org
Multichannel automatic speech recognition (ASR) systems commonly separate speech
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.

C Kim, A Misra, KK Chin, T Hughes, A Narayanan… - …, 2017 - research.google.com
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 …

A streaming on-device end-to-end model surpassing server-side conventional model quality and latency

TN Sainath, Y He, B Li, A Narayanan… - ICASSP 2020-2020 …, 2020 - ieeexplore.ieee.org
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 …

[PDF][PDF] Acoustic Modeling for Google Home.

B Li, TN Sainath, A Narayanan, J Caroselli… - Interspeech, 2017 - isca-archive.org
This paper describes the technical and system building advances made to the Google
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 …

From audio to semantics: Approaches to end-to-end spoken language understanding

P Haghani, A Narayanan, M Bacchiani… - 2018 IEEE Spoken …, 2018 - ieeexplore.ieee.org
Conventional spoken language understanding systems consist of two main components: an
automatic speech recognition module that converts audio to a transcript, and a natural …

Recognizing long-form speech using streaming end-to-end models

A Narayanan, R Prabhavalkar, CC Chiu… - 2019 IEEE automatic …, 2019 - ieeexplore.ieee.org
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-…