Developing high-performance speech processing systems for low-resource languages is very challenging. One approach to address the lack of resources is to make use of data from multiple languages. A popular direction in recent years is to train a multi-language bottleneck DNN. Language dependent and/or multi-language (all training languages) Tandem acoustic models (AM) are then trained. This work considers a particular scenario where the target language is unseen in multi-language training and has limited language model training data, a limited lexicon, and acoustic training data without transcriptions. A zero acoustic resources case is first described where a multi-language AM is directly applied, as a language independent AM (LIAM), to an unseen language. Secondly, in an unsupervised approach a LIAM is used to obtain hypotheses for the target language acoustic data transcriptions which are then used in training a language dependent AM. 3 languages from the IARPA Babel project are used for assessment: Vietnamese, Haitian Creole and Bengali. Performance of the zero acoustic resources system is found to be poor, with keyword spotting at best 60% of language dependent performance. Unsupervised language dependent training yields performance gains. For one language (Haitian Creole) the Babel target is achieved on the in-vocabulary data.
Cite as: Knill, K.M., Gales, M.J.F., Ragni, A., Rath, S.P. (2014) Language independent and unsupervised acoustic models for speech recognition and keyword spotting. Proc. Interspeech 2014, 16-20, doi: 10.21437/Interspeech.2014-4
@inproceedings{knill14_interspeech,
author={Kate M. Knill and Mark J. F. Gales and Anton Ragni and Shakti P. Rath},
title={{Language independent and unsupervised acoustic models for speech recognition and keyword spotting}},
year=2014,
booktitle={Proc. Interspeech 2014},
pages={16--20},
doi={10.21437/Interspeech.2014-4}
}