Sciweavers

ICASSP
2008
IEEE
14 years 5 months ago
An iterative unsupervised learning method for information distillation
Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interes...
Kamand Kamangar, Dilek Hakkani-Tür, Gökh...
ICASSP
2008
IEEE
14 years 5 months ago
Maximum entropy models for speech confidence estimation
In this work we implement a confidence estimation system based on a Naive Bayes classifier, by using the maximum entropy paradigm. The model takes information from various sourc...
Claudio Estienne, Alberto Sanchís, Alfons J...
ICASSP
2008
IEEE
14 years 5 months ago
Confidence estimation, OOV detection and language ID using phone-to-word transduction and phone-level alignments
Automatic Speech Recognition (ASR) systems continue to make errors during search when handling various phenomena including noise, pronunciation variation, and out of vocabulary (O...
Christopher M. White, Geoffrey Zweig, Lukas Burget...
ICASSP
2008
IEEE
14 years 5 months ago
High rate data hiding in ACELP speech codecs
A new method for hiding digital data in the bitstream of an ACELP speech codec is proposed in this paper. The key element of our method is an alternative search strategy for the A...
Bernd Geiser, Peter Vary
ICASSP
2008
IEEE
14 years 5 months ago
An empirical study of automatic accent classification
This paper extends language identification (LID) techniques to a large scale accent classification task: 23-way classification of foreign-accented English. We find that a pure...
Ghinwa F. Choueiter, Geoffrey Zweig, Patrick Nguye...
ICASSP
2008
IEEE
14 years 5 months ago
Improved GMM-based language recognition using constrained MLLR transforms
In this paper we describe the application of a feature-space transform based on constrained maximum likelihood linear regression for unsupervised compensation of channel and speak...
Wade Shen, Douglas A. Reynolds
ICASSP
2008
IEEE
14 years 5 months ago
Tracking analysis of the constant modulus algorithm
Recently, we proposed a model for the steady-state estimation error of real-valued constant-modulus-based algorithms as a function of the a priori error and of a term that measure...
Magno T. M. Silva, Vitor H. Nascimento
ICASSP
2008
IEEE
14 years 5 months ago
Quick fmllr for speaker adaptation in speech recognition
Balakrishnan Varadarajan, Daniel Povey, Selina M. ...
ICASSP
2008
IEEE
14 years 5 months ago
Deploying GOOG-411: Early lessons in data, measurement, and testing
We describe our early experience building and optimizing GOOG-411, a fully automated, voice-enabled, business finder. We show how taking an iterative approach to system developme...
Michiel Bacchiani, Françoise Beaufays, Joha...
ICASSP
2008
IEEE
14 years 5 months ago
Assessing the challenges of environmental signal processing through the sensorscope project
SensorScope is a collaborative project between network, signal processing, and environmental researchers that aims at providing a cheap and out-of-the-box environmental monitoring...
Guillermo Barrenetxea, François Ingelrest, ...