Sciweavers

TASLP
2008
141views more  TASLP 2008»
13 years 11 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
TASLP
2008
175views more  TASLP 2008»
13 years 11 months ago
A Variable Step-Size Affine Projection Algorithm Designed for Acoustic Echo Cancellation
Abstract--The adaptive algorithms used for acoustic echo cancellation (AEC) have to provide 1) high convergence rates and good tracking capabilities, since the acoustic environment...
Constantin Paleologu, Jacob Benesty, Silviu Ciochi...
TASLP
2008
108views more  TASLP 2008»
13 years 11 months ago
An Online Relevant Set Algorithm for Statistical Machine Translation
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
Christoph Tillmann, Tong Zhang
TASLP
2008
75views more  TASLP 2008»
13 years 11 months ago
Efficient Index-Based Audio Matching
Given a large audio database of music recordings, the goal of classical audio identification is to identify a particular audio recording by means of a short audio fragment. Even th...
Frank Kurth, Meinard Müller
TASLP
2008
71views more  TASLP 2008»
13 years 11 months ago
Dual-Source Transfer-Function Generalized Sidelobe Canceller
Full duplex hands-free man/machine interface often suffers from directional non-stationary interference (such as a competing speaker or an echo signal) as well as a stationary int...
Gal Reuven, Sharon Gannot, Israel Cohen
TASLP
2008
142views more  TASLP 2008»
13 years 11 months ago
HMM Word and Phrase Alignment for Statistical Machine Translation
HMM-based models are developed for the alignment of words and phrases in bitext. The models are formulated so that alignment and parameter estimation can be performed efficiently....
Yonggang Deng, William J. Byrne
TASLP
2008
117views more  TASLP 2008»
13 years 11 months ago
Auditory-Based Spectral Amplitude Estimators for Speech Enhancement
We propose a new family of Bayesian estimators for speech enhancement where the cost function includes both a power law and a weighting factor. The parameters of the cost function,...
Eric Plourde, Benoît Champagne
TASLP
2008
129views more  TASLP 2008»
13 years 11 months ago
Chroma Binary Similarity and Local Alignment Applied to Cover Song Identification
Abstract--We present a new technique for audio signal comparison based on tonal subsequence alignment and its application to detect cover versions (i.e., different performances of ...
Joan Serrà, Emilia Gómez, Perfecto H...
TASLP
2008
112views more  TASLP 2008»
13 years 11 months ago
A Study in Efficiency and Modality Usage in Multimodal Form Filling Systems
The usage patterns of speech and visual input modes are investigated as a function of relative input mode efficiency for both desktop and personal digital assistant (PDA) working ...
Manolis Perakakis, Alexandros Potamianos
TASLP
2008
84views more  TASLP 2008»
13 years 11 months ago
Searching Musical Audio Using Symbolic Queries
Finding a piece of music based on its content is a key problem in music information retrieval. For example, a user may be interested in finding music based on knowledge of only a s...
Iman S. H. Suyoto, Alexandra L. Uitdenbogerd, Falk...