Sciweavers

54 search results - page 5 / 11
» A new HMM training and testing scheme
Sort
View
IJCAI
2003
15 years 7 months ago
Does a New Simple Gaussian Weighting Approach Perform Well in Text Categorization?
A new approach to the Text Categorization problem is here presented. It is called Gaussian Weighting and it is a supervised learning algorithm that, during the training phase, est...
Giorgio Maria Di Nunzio, Alessandro Micarelli
ICASSP
2009
IEEE
16 years 23 days ago
Robust discriminative keyword spotting for emotionally colored spontaneous speech using bidirectional LSTM networks
In this paper we propose a new technique for robust keyword spotting that uses bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets to incorporate contextual informa...
Martin Wöllmer, Florian Eyben, Joseph Keshet,...
ICASSP
2010
IEEE
15 years 6 months ago
HMM-based separation of acoustic transfer function for single-channel sound source localization
This paper presents a sound source (talker) localization method using only a single microphone, where a HMM (Hidden Markov Model) of clean speech is introduced to estimate the aco...
Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki
ICASSP
2011
IEEE
14 years 9 months ago
Exemplar-based Sparse Representation phone identification features
Exemplar-based techniques, such as k-nearest neighbors (kNNs) and Sparse Representations (SRs), can be used to model a test sample from a few training points in a dictionary set. ...
Tara N. Sainath, David Nahamoo, Bhuvana Ramabhadra...
FGCS
1992
103views more  FGCS 1992»
15 years 7 months ago
Parallel Inference Machine PIM
: There have been no major control problems during the first three years of the new Tokaido-Sanyo Shinkansen (bullet train) Programmed Route Control (PRC) computer system. Prior to...
Kazuo Taki