Sciweavers

208 search results - page 27 / 42
» A Non-negative Approach to Language Informed Speech Separati...
Sort
View
92
Voted
EMNLP
2009
14 years 7 months ago
A Bayesian Model of Syntax-Directed Tree to String Grammar Induction
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...
Trevor Cohn, Phil Blunsom
WWW
2011
ACM
14 years 4 months ago
Two-stream indexing for spoken web search
This paper presents two-stream processing of audio to index the audio content for Spoken Web search. The first stream indexes the meta-data associated with a particular audio doc...
Jitendra Ajmera, Anupam Joshi, Sougata Mukherjea, ...
JAIR
2010
142views more  JAIR 2010»
14 years 8 months ago
Context-based Word Acquisition for Situated Dialogue in a Virtual World
To tackle the vocabulary problem in conversational systems, previous work has applied unsupervised learning approaches on co-occurring speech and eye gaze during interaction to au...
Shaolin Qu, Joyce Yue Chai
SIGIR
2003
ACM
15 years 2 months ago
Transliteration of proper names in cross-language applications
Translation of proper names is generally recognized as a significant problem in many multi-lingual text and speech processing applications. Even when large bilingual lexicons use...
Paola Virga, Sanjeev Khudanpur
72
Voted
UML
2005
Springer
15 years 3 months ago
Explicit Platform Models for MDA
The main drive for Model-Driven Architecture is that many software applications have to be deployed on a variety of platforms. The way MDA achieves this is by transforming a platfo...
Dennis Wagelaar, Viviane Jonckers