Sciweavers

ICASSP
2010
IEEE
13 years 5 months ago
Music dereverberation using harmonic structure source model and Wiener filter
This paper proposes a dereverberation method for musical audio signals. Existing dereverberation methods are designed for speech signals and are not necessarily effective for supp...
Naoki Yasuraoka, Takuya Yoshioka, Tomohiro Nakatan...
ICASSP
2010
IEEE
13 years 5 months ago
Optimizing spectral subtraction and wiener filtering for robust speech recognition in reverberant and noisy conditions
Speech enhancement is a common approach to address the effects of degradation due to noise and channel contamination. This approach is intended to suppress unwanted signal and rec...
Randy Gomez, Tatsuya Kawahara
ICASSP
2010
IEEE
13 years 5 months ago
Direct importance estimation with probabilistic principal component analyzers
The importance estimation problem (estimating the ratio of two probability density functions) has recently gathered a great deal of attention for use in various applications, e.g....
Makoto Yamada, Masashi Sugiyama, Gordon Wichern
ICASSP
2010
IEEE
13 years 5 months ago
Bridge detection and robust geodesics estimation via random walks
We propose an algorithm for detecting bridges and estimating geodesic distances from a set of noisy samples of an underlying manifold. Finding geodesics on a nearest neighbors gra...
Eugene Brevdo, Peter J. Ramadge
ICASSP
2010
IEEE
13 years 5 months ago
A comparison of nonstaggered compact FDTD schemes for the 3D wave equation
This paper aims at providing a better insight into the 3D approximations of the wave equation using compact finite-difference timedomain (FDTD) schemes in the context of room aco...
Konrad Kowalczyk, Maarten van Walstijn
ICASSP
2010
IEEE
13 years 5 months ago
Statistics of natural image distortions
Natural scene statistics (NSS) are an active area of research. Although there exist elegant models for NSS, the statistics of natural image distortions have received little attent...
Anush K. Moorthy, Alan C. Bovik
ICASSP
2010
IEEE
13 years 5 months ago
Source-domain adaptive filtering for MIMO systems with application to acoustic echo cancellation
Combining the channels of a multiple input/multiple output (MIMO) system into suitably chosen modes by a domain transformation offers great improvements of adaptive filtering alg...
Karim Helwani, Herbert Buchner, Sascha Spors
ICASSP
2010
IEEE
13 years 5 months ago
Multi-style MLP features for BN transcription
It has become common practice to adapt acoustic models to specific-conditions (gender, accent, bandwidth) in order to improve the performance of speech-to-text (STT) transcriptio...
Viet-Bac Le, Lori Lamel, Jean-Luc Gauvain
ICASSP
2010
IEEE
13 years 5 months ago
Robust spectro-temporal features based on autoregressive models of Hilbert envelopes
In this paper, we present a robust spectro-temporal feature extraction technique using autoregressive models (AR) of sub-band Hilbert envelopes. AR models of Hilbert envelopes are...
Sriram Ganapathy, Samuel Thomas, Hynek Hermansky