Sciweavers

ICASSP
2011
IEEE
13 years 3 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...
ICASSP
2011
IEEE
13 years 3 months ago
Experiments in context-independent recognition of non-lexical 'yes' or 'no' responses
We present our experiments in context-free recognition of non-lexical responses. Non-lexical verbal responses such as mmm-hmm or uh-huh are used by listeners to signal confirmati...
Shiva Sundaram, Robert Schleicher, Nathalie Diehl
ICASSP
2011
IEEE
13 years 3 months ago
Joint blind estimation of carrier phase and frequency offset for QAM signals using circular harmonic decomposition
An algorithm is presented for joint blind estimation of carrier phase and frequency offset for signals with quadrature amplitude modulation (QAM). The algorithm is based on a circ...
Alexander B. Sergienko, Alexander V. Petrov
ICASSP
2011
IEEE
13 years 3 months ago
Training of error-corrective model for ASR without using audio data
This paper introduces a method to train an error-corrective model for Automatic Speech Recognition (ASR) without using audio data. In existing techniques, it is assumed that suf...
Gakuto Kurata, Nobuyasu Itoh, Masafumi Nishimura
ICASSP
2011
IEEE
13 years 3 months ago
Support vector regression fusion scheme in phone duration modeling
A fusion scheme of phone duration models (PDMs) is presented in this work. Specifically, a support vector regression (SVR)-fusion model is fed with the predictions of a group of i...
Alexandros Lazaridis, Iosif Mporas, Todor Ganchev,...
ICASSP
2011
IEEE
13 years 3 months ago
Speech synthesis using HMM based diphone inventory encoding for low-resource devices
In this paper we describe the compression of diphone inventories used by the acoustic synthesis of a concatenative synthesis system. The inventory compression is based on a codebo...
Guntram Strecha, Matthias Wolff
ICASSP
2011
IEEE
13 years 3 months ago
Beating nyquist through correlations: A constrained random demodulator for sampling of sparse bandlimited signals
Technological constraints severely limit the rate at which analog-todigital converters can reliably sample signals. Recently, Tropp et al. proposed an architecture, termed the ran...
Andrew Harms, Waheed U. Bajwa, A. Robert Calderban...
ICASSP
2011
IEEE
13 years 3 months ago
Estimating note intensities in music recordings
In this paper, we present automated methods for estimating note intensities in music recordings. Given a MIDI file (representing the score) and an audio recording (representing a...
Sebastian Ewert, Meinard Müller
ICASSP
2011
IEEE
13 years 3 months ago
Score informed audio source separation using a parametric model of non-negative spectrogram
In this paper we present a new technique for monaural source separation in musical mixtures, which uses the knowledge of the musical score. This information is used to initialize ...
Romain Hennequin, Bertrand David, Roland Badeau
ICASSP
2011
IEEE
13 years 3 months ago
Improving head-related impulse response measured in noisy environments with spatio-temporal frequency analysis
A new noise reduction method based on spatio-temporal frequency analysis is proposed that can be applied to head-related impulse response (HRIR), which is an impulse response betw...
Takanori Nishino, Kazuya Takeda