Sciweavers

ICASSP
2009
IEEE
13 years 11 months ago
Dirichlet process mixture models with multiple modalities
The Dirichlet process can be used as a nonparametric prior for an infinite-dimensional probability mass function on the parameter space of a mixture model. The set of parameters o...
John William Paisley, Lawrence Carin
ICASSP
2009
IEEE
13 years 11 months ago
Improved lattice-based spoken document retrieval by directly learning from the evaluation measures
Lattice-based approaches have been widely used in spoken document retrieval to handle the speech recognition uncertainty and errors. Position Specific Posterior Lattices (PSPL) an...
Chao-hong Meng, Hung-yi Lee, Lin-shan Lee
ICASSP
2009
IEEE
13 years 11 months ago
Neural network based language models for highly inflective languages
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
Tomas Mikolov, Jirí Kopecký, Lukas B...
ICASSP
2009
IEEE
13 years 11 months ago
The expected amplitude of overlapping partials of harmonic sounds
In analyzing polyphonic signals, the handling of overlapping partials is one important problem. The assumptions usually made for partial overlaps are the additivity of the linear ...
Chunghsin Yeh, Axel Roebel
ICASSP
2009
IEEE
13 years 11 months ago
Robust word boundary detection in spontaneous speech using acoustic and lexical cues
We consider the problem of word boundary detection in spontaneous speech utterances. Acoustic features have been well explored in the literature in the context of word boundary de...
Andreas Tsiartas, Prasanta K. Ghosh, Panayiotis G....
ICASSP
2009
IEEE
13 years 11 months ago
Strategies for modeling reverberant speech in the feature domain
The length of the room impulse response characterizing the acoustic path between speaker and microphone is significantly larger than the length of the analysis window used for fea...
Armin Sehr, Walter Kellermann
ICASSP
2009
IEEE
13 years 11 months ago
A fast feature extraction method
A fast subspace analysis and feature extraction algorithm is proposed which is based on fast Haar transform and integral vector. In rapid object detection and conventional binary ...
Jing Pan, Yanwei Pang, Xuelong Li, Yuan Yuan, Dach...
ICASSP
2009
IEEE
13 years 11 months ago
Improved clustered hierarchical tandem system with bottom-up processing
The outputs of multi-layer perceptron (MLP) classifiers have been successfully used in tandem systems as features for HMM-based automatic speech recognition. In a previous paper, ...
Shuo-Yiin Chang, Lin-Shan Lee
ICASSP
2009
IEEE
13 years 11 months ago
Principal component analysis in decomposable Gaussian graphical models
We consider principal component analysis (PCA) in decomposable Gaussian graphical models. We exploit the prior information in these models in order to distribute its computation. ...
Ami Wiesel, Alfred O. Hero III
ICASSP
2009
IEEE
13 years 11 months ago
High-level feature extraction using SVM with walk-based graph kernel
We investigate a method using support vector machines (SVMs) with walk-based graph kernels for high-level feature extraction from images. In this method, each image is first segme...
Jean-Philippe Vert, Tomoko Matsui, Shin'ichi Satoh...