Sciweavers

2047 search results - page 50 / 410
» The limits of speech recognition
Sort
View
ANLP
2000
148views more  ANLP 2000»
13 years 10 months ago
Minimizing Word Error Rate in Textual Summaries of Spoken Language
Automatic generation of text summaries for spoken language faces the problem of containing incorrect words and passages due to speech recognition errors. This paper describes comp...
Klaus Zechner, Alex Waibel
SPEECH
2008
97views more  SPEECH 2008»
13 years 8 months ago
Extraction and representation of prosodic features for language and speaker recognition
In this paper, we propose a new approach for extracting and representing prosodic features directly from the speech signal. We hypothesize that prosody is linked to linguistic uni...
Leena Mary, B. Yegnanarayana
ACL
2007
13 years 10 months ago
NICT-ATR Speech-to-Speech Translation System
This paper describes the latest version of speech-to-speech translation systems developed by the team of NICT-ATR for over twenty years. The system is now ready to be deployed for...
Eiichiro Sumita, Tohru Shimizu, Satoshi Nakamura
CASES
2003
ACM
14 years 1 months ago
Architectural optimizations for low-power, real-time speech recognition
The proliferation of computing technology to low power domains such as hand–held devices has lead to increased interest in portable interface technologies, with particular inter...
Rajeev Krishna, Scott A. Mahlke, Todd M. Austin
ECAI
2008
Springer
13 years 10 months ago
Salience-driven Contextual Priming of Speech Recognition for Human-Robot Interaction
Abstract. The paper presents an implemented model for priming speech recognition, using contextual information about salient entities. The underlying hypothesis is that, in human-r...
Pierre Lison, Geert-Jan M. Kruijff