Speeding-up Neural Network Training Using Sentence and Frame Selection

被引：0

作者：

Scanzio, Stefano ^{[1
]}

Laface, Pietro ^{[1
]}

Gemello, Roberto ^{[2
]}

Mana, Franco ^{[2
]}

机构：

[1] Politecn Torino, Turin, Italy

[2] Loquendo, Turin, Italy

来源：

INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4 | 2007年

关键词：

speech recognition; neural networks training; sentence selection; frame selection;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Training Artificial Neural Networks (ANNs) with large amounts of speech data is a time intensive task due to the intrinsically sequential nature of the back-propagation algorithm. This paper presents an approach for training ANNs using sentence and frame selection. The goal is to speed-up the training process, and to balance the phonetic coverage of the selected frames, trying to mitigate the classification problems related to the prior probabilities of the individual phonetic classes. These techniques, together with a three-step training approach and software optimizations, reduced by an order of magnitude the training time of our models.

引用

页码：377 / +

页数：2

共 50 条

[21] Speeding Up the Training of Neural Networks with CUDA Technology
Chevitarese, Daniel Salles
Szwarcman, Dilza
Vellasco, Marley
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, PT I, 2012, 7267 : 30 - 38
[22] DeSpErate: Speeding-up Design Space Exploration by using Predictive Simulation Scheduling
Mariani, Giovanni
Palermo, Gianluca
Zaccaria, Vittorio
Silvano, Cristina
2014 DESIGN, AUTOMATION AND TEST IN EUROPE CONFERENCE AND EXHIBITION (DATE), 2014,
[23] Speeding-up the decision making of a learning agent using an ion trap quantum processor
Sriarunothai, Th
Woelk, S.
Giri, G. S.
Friis, N.
Dunjko, V
Briegel, H. J.
Wunderlich, Ch
QUANTUM SCIENCE AND TECHNOLOGY, 2019, 4 (01)
[24] Speeding up fuzzy clustering with neural network techniques
Borgelt, C
Kruse, R
PROCEEDINGS OF THE 12TH IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, VOLS 1 AND 2, 2003, : 852 - 856
[25] ShadowFS: Speeding-up Data Plane Monitoring and Telemetry using P4
Parizotto, Ricardo
Castanheira, Lucas
Ribeiro, Rafael Hengen
Arthur Selle Jacobs, Luciano Zembruzki
Granville, Lisandro Zambenedetti
Schaeffer-Filho, Alberto
ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2020,
[26] Speeding-Up the Particle Filter Algorithm for Tracking Multiple Targets Using CUDA Programming
Zhang, Jinhua
Guan, Wenkai
Ababei, Cristinel
Medeiros, Henry
Povinelli, Richard J.
2021 INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE AND COMPUTATIONAL INTELLIGENCE (CSCI 2021), 2021, : 1606 - 1610
[27] Speeding-up NCC-based template matching using parallel multimedia instructions
Di Stefano, L
Mattoccia, S
Tombari, F
CAMP 2005: SEVENTH INTERNATIONAL WORKSHOP ON COMPUTER ARCHITECTURE FOR MACHINE PERCEPTION , PROCEEDINGS, 2005, : 193 - 197
[28] Speeding-up Image Processing in Reaction-Diffusion Cellular Neural Networks using CUDA-enabled GPU Platforms
Stoica, George Valentin
Dogaru, Radu
Stoica, Elena Cristina
PROCEEDINGS OF THE 2014 6TH INTERNATIONAL CONFERENCE ON ELECTRONICS, COMPUTERS AND ARTIFICIAL INTELLIGENCE (ECAI), 2014,
[29] Using Supercomputer to Speed Up Neural Network Training
Yu, Yue
Chi, Xuebin
Jiang, Jinrong
2016 IEEE 22ND INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2016, : 942 - 947
[30] A first approach to speeding-up the inter mode selection in MPEG-2/H.264 transcoders using machine learning
Gerardo Fernández-Escribano
Hari Kalva
Pedro Cuenca
Luis Orozco-Barbosa
Multimedia Tools and Applications, 2007, 35 : 225 - 240

← 1 2 3 4 5 →