Sciweavers

8 search results - page 1 / 2
» Towards multi-speaker unsupervised speech pattern discovery
Sort
View
ICASSP
2010
IEEE
13 years 4 months ago
Towards multi-speaker unsupervised speech pattern discovery
In this paper, we explore the use of a Gaussian posteriorgram based representation for unsupervised discovery of speech patterns. Compared with our previous work, the new approach...
Yaodong Zhang, James R. Glass
TASLP
2008
141views more  TASLP 2008»
13 years 4 months ago
Unsupervised Pattern Discovery in Speech
We present a novel approach to speech processing based on the principle of pattern discovery. Our work represents a departure from traditional models of speech recognition, where t...
A. S. Park, J. R. Glass
ICASSP
2011
IEEE
12 years 8 months ago
Towards robust word discovery by self-similarity matrix comparison
Word discovery is the task of discovering and collecting occurrences of repeating words in the absence of prior acoustic and linguistic knowledge, or training material. The capabi...
Armando Muscariello, Guillaume Gravier, Fré...
PAMI
2008
159views more  PAMI 2008»
13 years 4 months ago
Analysis of Head Gesture and Prosody Patterns for Prosody-Driven Head-Gesture Animation
We propose a new two-stage framework for joint analysis of head gesture and speech prosody patterns of a speaker toward automatic realistic synthesis of head gestures from speech p...
Mehmet Emre Sargin, Yücel Yemez, Engin Erzin,...
MM
2005
ACM
146views Multimedia» more  MM 2005»
13 years 10 months ago
Unsupervised content discovery in composite audio
Automatically extracting semantic content from audio streams can be helpful in many multimedia applications. Motivated by the known limitations of traditional supervised approache...
Rui Cai, Lie Lu, Alan Hanjalic