650 search results - page 107 / 130 » Comparative Evaluation of Speech Parameterizations for Speec... |
104
click to vote
ICASSP
2009
IEEE
15 years 8 months ago
2009
IEEE
In the Weighted Finite State Transducer (WFST) framework for speech recognition, we can reduce memory usage and increase flexibility by using on-the-fly composition which genera...
104
click to vote
EMNLP
2008
15 years 2 months ago
2008
Confusion networks are a simple representation of multiple speech recognition or translation hypotheses in a machine translation system. A typical operation on a confusion network...
EMNLP
2008
15 years 2 months ago
2008
Predicting possible code-switching points can help develop more accurate methods for automatically processing mixed-language text, such as multilingual language models for speech ...
ACL
2001
15 years 2 months ago
2001
In this paper we address the problem of extracting key pieces of information from voicemail messages, such as the identity and phone number of the caller. This task differs from t...
ACL
1996
15 years 2 months ago
1996
This paper describes a system that leads us to believe in the feasibility of constructing natural spoken dialogue systems in task-oriented domains. It specifically addresses the i...