Sciweavers

27 search results - page 5 / 6
» Training and adapting MLP features for Arabic speech recogni...
Sort
View
INTERSPEECH
2010
13 years 2 days ago
Towards mixed language speech recognition systems
Multilingual speech recognition obviously involves numerous research challenges, including common phoneme sets, adaptation on limited amount of training data, as well as mixed lan...
David Imseng, Hervé Bourlard, Mathew Magima...
LREC
2010
164views Education» more  LREC 2010»
13 years 6 months ago
Practical Evaluation of Speech Recognizers for Virtual Human Dialogue Systems
We perform a large-scale evaluation of multiple off-the-shelf speech recognizers across diverse domains for virtual human dialogue systems. Our evaluation is aimed at speech recog...
Xuchen Yao, Pravin Bhutada, Kallirroi Georgila, Ke...
ICASSP
2008
IEEE
13 years 11 months ago
Toward a detector-based universal phone recognizer
In recent research, we have proposed a high-accuracy bottom-up detection-based paradigm for continuous phone speech recognition. The key component of our system was a bank of arti...
Sabato Marco Siniscalchi, Torbjørn Svendsen...
CLEAR
2007
Springer
144views Biometrics» more  CLEAR 2007»
13 years 11 months ago
The SRI-ICSI Spring 2007 Meeting and Lecture Recognition System
We describe the latest version of the SRI-ICSI meeting and lecture recognition system, as was used in the NIST RT-07 evaluations, highlighting improvements made over the last year....
Andreas Stolcke, Xavier Anguera, Kofi Boakye, &Oum...
IJCNN
2006
IEEE
13 years 11 months ago
Adaptation of Artificial Neural Networks Avoiding Catastrophic Forgetting
— In connectionist learning, one relevant problem is “catastrophic forgetting” that may occur when a network, trained with a large set of patterns, has to learn new input pat...
Dario Albesano, Roberto Gemello, Pietro Laface, Fr...