Sciweavers

ICASSP
2008
IEEE
13 years 10 months ago
Automatic lecture transcription by exploiting presentation slide information for language model adaptation
The paper addresses language model adaptation for automatic lecture transcription by fully exploiting presentation slide information used in the lecture. As the text in the presen...
Tatsuya Kawahara, Yusuke Nemoto, Yuya Akita
ICASSP
2008
IEEE
13 years 10 months ago
Portuguese variety identification on broadcast news
This paper describes an accent identification system for Portuguese, that explores different type of properties: acoustic, phonotactic and prosodic. The system is designed to be ...
Jean-Luc Rouas, Isabel Trancoso, Céu Viana,...
ICASSP
2008
IEEE
13 years 10 months ago
Voice source cepstrum coefficients for speaker identification
We propose a novel feature set for speaker recognition that is based on the voice source signal. The feature extraction process uses closed-phase LPC analysis to estimate the voca...
Jon Gudnason, Mike Brookes
ICASSP
2008
IEEE
13 years 10 months ago
Average case analysis of sparse recovery with thresholding : New bounds based on average dictionary coherence
This paper analyzes the performance of the simple thresholding algorithm for sparse signal representations. In particular, in order to be more realistic we introduce a new probabi...
Mohammad Golbabaee, Pierre Vandergheynst
ICASSP
2008
IEEE
13 years 10 months ago
Variance reduction with neighborhood smoothing for local intrinsic dimension estimation
Local intrinsic dimension estimation has been shown to be useful for many tasks such as image segmentation, anomaly detection, and de-biasing global dimension estimates. Of partic...
Kevin M. Carter, Alfred O. Hero
ICASSP
2008
IEEE
13 years 10 months ago
Fast speaker adaptation using non-negative matrix factorization
This paper describes a new method for fast speaker adaptation in large vocabulary recognition systems. As in most HMM-based recognizers, the observation densities are modeled as a...
Jacques Duchateau, Tobias Leroy, Kris Demuynck, Hu...
ICASSP
2008
IEEE
13 years 10 months ago
A novel a priori SNR estimation approach based on selective cepstro-temporal smoothing
While state-of-the-art approaches obtain an estimate of the a priori SNR by adaptively smoothing its maximum likelihood estimate in the frequency domain, we selectively smooth the...
Colin Breithaupt, Timo Gerkmann, Rainer Martin
ICASSP
2008
IEEE
13 years 10 months ago
Punctuating speech for information extraction
This paper studies the effect of automatic sentence boundary detection and comma prediction on entity and relation extraction in speech. We show that punctuating the machine gener...
Benoît Favre, Ralph Grishman, Dustin Hillard...
ICASSP
2008
IEEE
13 years 10 months ago
Brute-forcing hierarchical functionals for paralinguistics: A waste of feature space?
While the ”‘quasi-state-of-the-art”’ towards acoustic emotion recognition relies on multivariate time-series analysis of e.g. pitch, energy, or MFCC by statistical functio...
Björn Schuller, Matthias Wimmer, Lorenz Moese...
ICASSP
2008
IEEE
13 years 10 months ago
Cepstral domain feature compensation based on diagonal approximation
In this paper, we propose a novel approach to feature compensation performed in the cepstral domain. We apply the linear approximation method in the cepstral domain to simplify th...
Woohyung Lim, Chang Woo Han, Jong Won Shin, Nam So...