2 |
Comparative Study on Sentence Boundary Prediction for German and English Broadcast News
|
|
|
|
In: http://infoscience.epfl.ch/record/229982 (2017)
|
|
BASE
|
|
Show details
|
|
3 |
Exploiting foreign resources for DNN-based ASR
|
|
|
|
In: http://infoscience.epfl.ch/record/210038 (2015)
|
|
BASE
|
|
Show details
|
|
4 |
Exploiting foreign resources for DNN-based ASR
|
|
|
|
In: http://infoscience.epfl.ch/record/210027 (2015)
|
|
BASE
|
|
Show details
|
|
6 |
Automatic Speech Recognition and Translation of a Swiss German Dialect: Walliserdeutsch
|
|
|
|
In: http://infoscience.epfl.ch/record/202570 (2014)
|
|
BASE
|
|
Show details
|
|
7 |
Development of Bilingual ASR System for MediaParl Corpus
|
|
|
|
In: http://infoscience.epfl.ch/record/203858 (2014)
|
|
BASE
|
|
Show details
|
|
8 |
Multilingual Deep Neural Network based Acoustic Modeling For Rapid Language Adaptation
|
|
|
|
In: http://infoscience.epfl.ch/record/198446 (2014)
|
|
BASE
|
|
Show details
|
|
9 |
Posterior-based Sparse Representation for Automatic Speech Recognition
|
|
|
|
In: http://infoscience.epfl.ch/record/200299 (2014)
|
|
BASE
|
|
Show details
|
|
10 |
Development of Bilingual ASR System for MediaParl Corpus
|
|
|
|
In: http://infoscience.epfl.ch/record/203869 (2014)
|
|
BASE
|
|
Show details
|
|
12 |
Multilingual speech recognition:a posterior based approach ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Comparing different acoustic modeling techniques for multilingual boosting
|
|
|
|
In: http://infoscience.epfl.ch/record/192725 (2013)
|
|
BASE
|
|
Show details
|
|
15 |
Using out-of-language data to improve an under-resourced speech recognizer
|
|
|
|
In: http://infoscience.epfl.ch/record/192457 (2013)
|
|
Abstract:
Under-resourced speech recognizers may benefit from data in languages other than the target language. In this paper, we report how to boost the performance of an Afrikaans automatic speech recognition system by using already available Dutch data. We successfully exploit available multilingual resources through 1) posterior features, estimated by multilayer perceptrons (MLP) and 2) subspace Gaussian mixture models (SGMMs). Both the MLPs and the SGMMs can be trained on out-of-language data. We use three different acoustic modeling techniques, namely Tandem, Kullback-Leibler divergence based HMMs (KL-HMM) as well as SGMMs and show that the proposed multilingual systems yield 12% relative improvement compared to a conventional monolingual HMM/GMM system only trained on Afrikaans. We also show that KL-HMMs are extremely powerful for under-resourced languages: using only six minutes of Afrikaans data (in combination with out-of-language data), KL-HMM yields about 30% relative improvement compared to conventional maximum likelihood linear regression and maximum a posteriori based acoustic model adaptation.
|
|
URL: http://infoscience.epfl.ch/record/192457 http://publications.idiap.ch/index.php/publications/showcite/Imseng_SPECOM_2013 http://infoscience.epfl.ch/record/192457/files/Imseng_Idiap-RR-09-2013.pdf
|
|
BASE
|
|
Hide details
|
|
16 |
Boosting under-resourced speech recognizers by exploiting out of language data - Case study on Afrikaans
|
|
|
|
In: http://infoscience.epfl.ch/record/192728 (2013)
|
|
BASE
|
|
Show details
|
|
17 |
Multilingual speech recognition:a posterior based approach
|
|
|
|
In: http://infoscience.epfl.ch/record/187003 (2013)
|
|
BASE
|
|
Show details
|
|
18 |
Application of Subspace Gaussian Mixture Models in Contrastive Acoustic Scenarios
|
|
|
|
In: http://infoscience.epfl.ch/record/192544 (2013)
|
|
BASE
|
|
Show details
|
|
19 |
Applying Multi- and Cross-Lingual Stochastic Phone Space Transformations to Non-Native Speech Recognition
|
|
|
|
In: http://infoscience.epfl.ch/record/189424 (2013)
|
|
BASE
|
|
Show details
|
|
20 |
Using out-of-language data to improve an under-resourced speech recognizer
|
|
|
|
In: http://infoscience.epfl.ch/record/192727 (2013)
|
|
BASE
|
|
Show details
|
|
|
|