Sciweavers

367 search results - page 59 / 74
» Large-Vocabulary Speech Recognition Algorithms
Sort
View
ICASSP
2008
IEEE
15 years 3 months ago
Discriminative feature selection for hidden Markov models using Segmental Boosting
We address the feature selection problem for hidden Markov models (HMMs) in sequence classification. Temporal correlation in sequences often causes difficulty in applying featur...
Pei Yin, Irfan A. Essa, Thad Starner, James M. Reh...
CRV
2006
IEEE
206views Robotics» more  CRV 2006»
15 years 3 months ago
Toward an Application of Content-Based Video Indexing to Computer- Assisted Descriptive Video
This paper presents the status of a project targeting the development of content-based video indexing tools, to assist a human in the generation of descriptive video for the hard ...
Langis Gagnon, France Laliberté, Marc Lalon...
IEEEMSP
2002
IEEE
117views Multimedia» more  IEEEMSP 2002»
15 years 2 months ago
Hidden Markov model for automatic transcription of MIDI signals
— This paper describes a Hidden Markov Model (HMM)-based method of automatic transcription of MIDI (Musical Instrument Digital Interface) signals of performed music. The problem ...
Haruto Takeda, Naoki Saito, Tomoshi Otsuki, Mitsur...
ICASSP
2011
IEEE
14 years 1 months ago
Bayesian reinforcement learning for POMDP-based dialogue systems
Spoken dialogue systems are gaining popularity with improvements in speech recognition technologies. Dialogue systems can be modeled effectively using POMDPs, achieving improvemen...
ShaoWei Png, Joelle Pineau
MM
2005
ACM
126views Multimedia» more  MM 2005»
15 years 3 months ago
A corpus-based singing voice synthesis system for mandarin Chinese
In this paper, the design and implementation of a corpus-based singing voice synthesis (SVS) system for Mandarin Chinese was introduced. The design rules of three corpora for sing...
Cheng-Yuan Lin, Tzu-Ying Lin, Jyh-Shing Roger Jang