Paper Info
Title
Implementing SRI's Pashto speech-to-speech translation system on a smart phone
Abstract
We describe our recent effort implementing SRI's UMPC-based Pashto speech-to-speech (S2S) translation system on a smart phone running the Android operating system. In order to maintain very low latencies of system response on computationally limited smart phone platforms, we developed efficient algorithms and data structures and optimized model sizes for various system components. Our current Android-based S2S system requires less than one-fourth the system memory and significantly lower processor speed with a sacrifice of 15% relative loss of system accuracy, compared to a laptop-based platform.
Year
DOI
Venue
2010
10.1109/SLT.2010.5700835
SLT
Keywords
Field
DocType
optimisation,speech processing,mobile handsets,speech-to-speech translation,umpc,data structures,operating systems (computers),language translation,system memory,android operating system,pashto speech-to-speech translation system,sri,system response,android,natural language processing,mobile computing,processor speed,smart phone,operating system,data structure,mobile computer,hidden markov models,training data,low latency,memory management,speech recognition,decoding,data models
Mobile computing,Speech processing,Data modeling,Android (operating system),Language translation,Laptop,Computer science,Speech recognition,Memory management,Clock rate,Embedded system
Conference
ISBN
Citations 
PageRank 
978-1-4244-7902-3
0
0.34
References 
Authors
14
9
Name
Order
Citations
PageRank
Jing Zheng144243.00
Arindam Mandal215816.44
Xin Lei321919.36
Michael Frandsen4393.74
Necip Fazil Ayan533923.36
Dimitra Vergyri637336.97
Wen Wang732729.31
Murat Akbacak8869.86
Kristin Precoda99111.74