Title
A review of on-device fully neural end-to-end automatic speech recognition algorithms
Abstract
In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as an acoustic model, a language model, a pronunciation model, a text-normalizer, an inverse-text normalizer, a decoder based on a Weighted Finite State Transduce...
Year
DOI
Venue
2020
10.1109/IEEECONF51394.2020.9443456
2020 54th Asilomar Conference on Signals, Systems, and Computers
Keywords
DocType
ISBN
Transducers,Recurrent neural networks,Quantization (signal),Program processors,Computational modeling,Speech recognition,Classification algorithms
Conference
978-0-7381-3126-9
Citations 
PageRank 
References 
0
0.34
0
Authors
8
Name
Order
Citations
PageRank
Chanwoo Kim125328.44
Dhananjaya Gowda235.47
Dongsoo Lee323330.63
Jiyeon Kim402.37
Ankur N Kumar583.39
Sungsoo Kim611524.95
Abhinav Garg766.61
Changwoo Han801.01