Sciweavers

577 search results - page 58 / 116
» Improved Text Generation Using N-gram Statistics
Sort
View
ICASSP
2009
IEEE
14 years 4 months ago
Using a pitch-synchronous residual codebook for hybrid HMM/frame selection speech synthesis
This paper proposes a method to improve the quality delivered by statistical parametric speech synthesizers. For this, we use a codebook of pitch-synchronous residual frames, so a...
Thomas Drugman, Alexis Moinet, Thierry Dutoit, Geo...
COLING
2002
13 years 9 months ago
Lexical Query Paraphrasing for Document Retrieval
We describe a mechanism for the generation of lexical paraphrases of queries posed to an Internet resource. These paraphrases are generated using WordNet and part-of-speech inform...
Ingrid Zukerman, Bhavani Raskutti
ICASSP
2010
IEEE
13 years 10 months ago
Vocabulary and language model adaptation using just one speech file
This paper investigates unsupervised vocabulary and language model self-adaptation (VLA) from just one speech file using the web as a knowledge source and without prior knowledge...
Sha Meng, Kishan Thambiratnam, Yimeng Lin, Lifang ...
GECCO
2005
Springer
139views Optimization» more  GECCO 2005»
14 years 3 months ago
Use of a genetic algorithm in brill's transformation-based part-of-speech tagger
The tagging problem in natural language processing is to find a way to label every word in a text as a particular part of speech, e.g., proper noun. An effective way of solving th...
Garnett Carl Wilson, Malcolm I. Heywood
ICDE
2010
IEEE
200views Database» more  ICDE 2010»
14 years 4 months ago
GenerIE: Information extraction using database queries
— Information extraction systems are traditionally implemented as a pipeline of special-purpose processing modules. A major drawback of such an approach is that whenever a new ex...
Luis Tari, Phan Huy Tu, Jörg Hakenberg, Yi Ch...