Follow
Nikko Strom
Nikko Strom
Verified email at amazon.com - Homepage
Title
Cited by
Cited by
Year
Scalable distributed DNN training using commodity GPU cloud computing
N Ström
6772015
Method and system for selecting grammars based on geographic information associated with a caller
N Strom
US Patent 7,630,900, 2009
3582009
Histogram grammar weighting and error corrective training of grammar weights
N Ström, N Kibre
US Patent 6,985,862, 2006
2662006
Coarticulated concatenated speech
SJ Bailey, N Strom
US Patent 6,873,952, 2005
2352005
Adding audio effects to spoken utterance
N Strom
US Patent 7,644,000, 2010
2182010
Transmission of noise parameters for improving automatic speech recognition
RP Thomas, N Strom
US Patent 8,983,844, 2015
1872015
Distributed endpointing for speech recognition
HE Secker-Walker, KJ Basye, N Strom, RP Thomas
US Patent 9,818,407, 2017
1442017
Max-pooling loss training of long short-term memory networks for small-footprint keyword spotting
M Sun, A Raju, G Tucker, S Panchapagesan, G Fu, A Mandal, ...
2016 IEEE spoken language technology workshop (SLT), 474-480, 2016
1402016
Compressed time delay neural network for small-footprint keyword spotting
M Sun, D Snyder, Y Gao, V Nagaraja, M Rodehorst, S Panchapagesan, ...
1372017
Speech recognizer with multi-directional decoding
MME Bisani, N Strom, B Hoffmeister, RP Thomas
US Patent 9,286,897, 2016
1262016
Identifying candidate passwords from captured audio
RP Thomas, N Strom
US Patent 8,898,064, 2014
1142014
Lessons from building acoustic models with a million hours of speech
SHK Parthasarathi, N Strom
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
1002019
Phoneme probability estimation with dynamic sparsely connected artificial neural networks
N Ström
The Free Speech Journal 5 (1-41), 2, 1997
761997
Sparse connection and pruning in large dynamic artificial neural networks
N Ström
Fifth European Conference on Speech Communication and Technology, 1997
691997
Robust i-vector based adaptation of DNN acoustic model for speech recognition
S Garimella, A Mandal, N Ström, B Hoffmeister, S Matsoukas, ...
642015
Parse information encoding in a finite state transducer
N Strom, K Ramakrishnan
US Patent 8,972,243, 2015
632015
Direct modeling of raw audio with dnns for wake word detection
K Kumatani, S Panchapagesan, M Wu, M Kim, N Strom, G Tiwari, ...
2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU …, 2017
622017
The Waxholm system-a progress report
J Bertenstam, J Beskow, M Blomberg, R Carlson, K Elenius, B Granström, ...
Proceedings of Spoken Dialogue Systems, 1995
611995
Dialog management for multiple users
P Krishnan, A Mandal, SR Jonnalagadda, N Strom, A Rastrow, Y Shi, ...
US Patent 11,908,468, 2024
522024
Frequency domain multi-channel acoustic modeling for distant speech recognition
W Minhua, K Kumatani, S Sundaram, N Ström, B Hoffmeister
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
522019
The system can't perform the operation now. Try again later.
Articles 1–20