Sciweavers

379 search results - page 15 / 76
» Rating Compiler Optimizations for Automatic Performance Tuni...
Sort
View
CMMR
2004
Springer
97views Music» more  CMMR 2004»
14 years 1 months ago
Evolutionary Optimization of Music Performance Annotation
In this paper we present an enhancement of edit distance based music performance annotation. The annotation captures musical expressivity not only in terms of timing deviations but...
Maarten Grachten, Josep Lluís Arcos, Ramon ...
EMNLP
2009
13 years 5 months ago
Feasibility of Human-in-the-loop Minimum Error Rate Training
Minimum error rate training (MERT) involves choosing parameter values for a machine translation (MT) system that maximize performance on a tuning set as measured by an automatic e...
Omar Zaidan, Chris Callison-Burch
FPL
2009
Springer
172views Hardware» more  FPL 2009»
14 years 8 days ago
Performance comparison of single-precision SPICE Model-Evaluation on FPGA, GPU, Cell, and multi-core processors
Automated code generation and performance tuning techniques for concurrent architectures such as GPUs, Cell and FPGAs can provide integer factor speedups over multi-core processor...
Nachiket Kapre, André DeHon
ICS
2001
Tsinghua U.
14 years 3 days ago
Global optimization techniques for automatic parallelization of hybrid applications
This paper presents a novel technique to perform global optimization of communication and preprocessing calls in the presence of array accesses with arbitrary subscripts. Our sche...
Dhruva R. Chakrabarti, Prithviraj Banerjee
ICASSP
2011
IEEE
12 years 11 months ago
Why word error rate is not a good metric for speech recognizer training for the speech translation task?
Speech translation (ST) is an enabling technology for cross-lingual oral communication. A ST system consists of two major components: an automatic speech recognizer (ASR) and a ma...
Xiaodong He, Li Deng, Alex Acero