10.1184/R1/6473330.v1
Jonas Gehring
Jonas
Gehring
Quoc Bao Nguyen
Quoc Bao
Nguyen
Florian Metze
Florian
Metze
Alexander Waibel
Alexander
Waibel
DNN acoustic modeling with modular multi-lingual feature extraction networks
Carnegie Mellon University
2013
Deep Neural Networks
Multi-Lingual Acoustic Modeling
Large-Vocabulary Speech Recognition
Low-Resource Acoustic Modeling
2013-12-01 00:00:00
Journal contribution
https://kilthub.cmu.edu/articles/journal_contribution/DNN_acoustic_modeling_with_modular_multi-lingual_feature_extraction_networks/6473330
<p>In this work, we propose several deep neural network architectures that are able to leverage data from multiple languages. Modularity is achieved by training networks for extracting high-level features and for estimating phoneme state posteriors separately, and then combining them for decoding in a hybrid DNN/HMM setup. This approach has been shown to achieve superior performance for single-language systems, and here we demonstrate that feature extractors benefit significantly from being trained as multi-lingual networks with shared hidden representations. We also show that existing mono-lingual networks can be re-used in a modular fashion to achieve a similar level of performance without having to train new networks on multi-lingual data. Furthermore, we investigate in extending these architectures to make use of language-specific acoustic features. Evaluations are performed on a low-resource conversational telephone speech transcription task in Vietnamese, while additional data for acoustic model training is provided in Pashto, Tagalog, Turkish, and Cantonese. Improvements of up to 17.4% and 13.8% over mono-lingual GMMs and DNNs, respectively, are obtained.</p>