Sciweavers

24451 search results - page 4635 / 4891
» Research methods in information
Sort
View
INTERSPEECH
2010
15 years 1 months ago
Emotion recognition using imperfect speech recognition
This paper investigates the use of speech-to-text methods for assigning an emotion class to a given speech utterance. Previous work shows that an emotion extracted from text can c...
Florian Metze, Anton Batliner, Florian Eyben, Tim ...
INTERSPEECH
2010
15 years 1 months ago
FSM-based pronunciation modeling using articulatory phonological code
According to articulatory phonology, the gestural score is an invariant speech representation. Though the timing schemes, i.e., the onsets and offsets, of the gestural activations...
Chi Hu, Xiaodan Zhuang, Mark Hasegawa-Johnson
INTERSPEECH
2010
15 years 1 months ago
Boosted mixture learning of Gaussian mixture HMMs for speech recognition
In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models fo...
Jun Du, Yu Hu, Hui Jiang
JCIT
2010
149views more  JCIT 2010»
15 years 1 months ago
People Summarization by Combining Named Entity Recognition and Relation Extraction
The two most important tasks in entity information summarization from the Web are named entity recognition and relation extraction. Little work has been done toward an integrated ...
Xiaojiang Liu, Nenghai Yu
JCST
2010
189views more  JCST 2010»
15 years 1 months ago
Formally Analyzing Expected Time Complexity of Algorithms Using Theorem Proving
Probabilistic techniques are widely used in the analysis of algorithms to estimate the computational complexity of algorithms or a computational problem. Traditionally, such analys...
Osman Hasan, Sofiène Tahar
« Prev « First page 4635 / 4891 Last » Next »