Using resources from a closely-related language to develop ASR for a very under-resourced language: a case study for iban

This paper presents our strategies for developing an automatic speech recognition system for Iban, an under-resourced language. We faced several challenges such as no pronunciation dictionary and lack of training material for building acoustic models. To overcome these problems, we proposed approaches which exploit resources from a closely-related language (Malay). We developed a semi-supervised method for building the pronunciation dictionary and applied cross-lingual strategies for improving acoustic models trained with very limited training data. Both approaches displayed very encouraging results, which show that data from a closely-related language, if available, can be exploited to build ASR for a new language. In the final part of the paper, we present a zero-shot ASR using Malay resources that can be used as an alternative method for transcribing Iban speech.

[1]  Georg Heigold,et al.  Multilingual acoustic models using distributed deep neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[2]  Tanja Schultz,et al.  Automatic speech recognition for under-resourced languages: A survey , 2014, Speech Commun..

[3]  Etienne Barnard,et al.  The efficient generation of pronunciation dictionaries: human factors during bootstrapping , 2004, INTERSPEECH.

[4]  Paul Deléglise,et al.  TED-LIUM: an Automatic Speech Recognition dedicated corpus , 2012, LREC.

[5]  Brian Kingsbury,et al.  Lattice-based optimization of sequence classification criteria for neural-network acoustic modeling , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Tanja Schultz,et al.  Multilingual and Crosslingual Speech Recognition , 1998 .

[7]  Daniel Povey,et al.  The Kaldi Speech Recognition Toolkit , 2011 .

[8]  Bali Ranaivo-Malançon,et al.  Malay Grapheme to Phoneme Tool for Automatic Speech Recognition , 2009 .

[9]  Minematsu Nobuaki,et al.  Evaluations of an Open Source WFST-based Phoneticizer , 2011 .

[10]  Ramesh A. Gopinath,et al.  Maximum likelihood modeling with Gaussian distributions for classification , 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

[11]  Kai Feng,et al.  SUBSPACE GAUSSIAN MIXTURE MODELS FOR SPEECH RECOGNITION , 2009 .

[12]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[13]  Tanja Schultz,et al.  Fast bootstrapping of LVCSR systems with multilingual phoneme sets , 1997, EUROSPEECH.

[14]  Laurent Besacier,et al.  Fast Bootstrapping of Grapheme to Phoneme System for Under-resourced Languages - Application to the Iban Language , 2013 .

[15]  Yifan Gong,et al.  Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Hui Lin,et al.  A study on multilingual acoustic modeling for large vocabulary ASR , 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

[17]  Florian Metze,et al.  Improving low-resource CD-DNN-HMM using dropout and multilingual DNN training , 2013, INTERSPEECH.

[18]  Steve Renals,et al.  Unsupervised cross-lingual knowledge transfer in DNN-based LVCSR , 2012, 2012 IEEE Spoken Language Technology Workshop (SLT).

[19]  Kai Feng,et al.  The subspace Gaussian mixture model - A structured model for speech recognition , 2011, Comput. Speech Lang..

[20]  Tanja Schultz,et al.  Towards universal speech recognition , 2002, Proceedings. Fourth IEEE International Conference on Multimodal Interfaces.

[21]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition , 2012 .

[22]  Andreas Stolcke,et al.  SRILM - an extensible language modeling toolkit , 2002, INTERSPEECH.

[23]  Ngoc Thang Vu,et al.  Multilingual deep neural network based acoustic modeling for rapid language adaptation , 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  Solange Rossato,et al.  Semi-supervised G2p bootstrapping and its application to ASR for a very under-resourced language: Iban , 2014, SLTU.

[25]  Haizhou Li,et al.  MASS: A Malay language LVCSR corpus resource , 2009, 2009 Oriental COCOSDA International Conference on Speech Database and Assessments.

[26]  Tien Ping Tan,et al.  Analysis of Malay Speech Recognition for Different Speaker Origins , 2012, 2012 International Conference on Asian Language Processing.

[27]  Mark J. F. Gales,et al.  Maximum likelihood linear transformations for HMM-based speech recognition , 1998, Comput. Speech Lang..

[28]  Liang Lu,et al.  Cross-Lingual Subspace Gaussian Mixture Models for Low-Resource Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[29]  Petr Motlícek,et al.  Using out-of-language data to improve an under-resourced speech recognizer , 2014, Speech Communication.

[30]  Etienne Barnard,et al.  Bootstrapping in language resource generation , 2003 .