Investigation on cross- and multilingual MLP features under matched and mismatched acoustical conditions
Authors:
- 1 May 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 7349-7353
Abstract
In this paper, Multi Layer Perceptron (MLP) based multilingual bottleneck features are investigated for acoustic modeling in three languages - German, French, and US English. We use a modified training algorithm to handle the multilingual training scenario without having to explicitly map the phonemes to a common phoneme set. Furthermore, the cross-lingual portability of bottleneck features between the three languages are also investigated. Single pass recognition experiments on large vocabulary SMS dictation task indicate that (1) multilingual bottleneck features yield significantly lower word error rates compared to standard MFCC features (2) multilingual bottleneck features are superior to monolingual bottleneck features trained for the target language with limited training data, and (3) multilingual bottleneck features are beneficial in training acoustic models in a low resource language where only mismatched training data is available-by exploiting the more matched training data from other languages.Keywords
This publication has 13 references indexed in Scilit:
- Multilingual MLP features for low-resource LVCSR systems2012
- Strategies for using MLP based features with limited target-language training data2011
- Study of probabilistic and Bottle-Neck features in multilingual environment2011
- Cross-lingual portability of Chinese and english neural network features for French and German LVCSR2011
- Analysis and comparison of recent MLP features for LVCSR systems2011
- The RWTH 2010 Quaero ASR evaluation system for English, French, and German2011
- Cross-lingual and multi-stream posterior features for low resource LVCSR systems2010
- On the use of a multilingual neural network front-end2008
- Probabilistic and Bottle-Neck Features for LVCSR of Meetings2007
- Cross-Domain and Cross-Language Portability of Acoustic Features Estimated by Multilayer Perceptrons2006