Srikanth Madikeri(Idiap Research Institute), Banriskhem Kayang Khonglah(Idiap Research Institute), Sibo Tong(Idiap Research Institute), Petr Motlicek(Idiap Research Institute), Herve Bourlard(Idiap Research Institute & EPFL) and Dan Povey(Xiaomi, Inc.)
Multilingual acoustic model training combines data from multiple languages to train an automatic speech recognition system. Such a system is beneficial when training data for a target language is limited. Lattice-Free Maximum Mutual Information (LF-MMI) training performs sequence discrimination by introducing competing hypotheses through a denominator graph in the cost function. The standard approach to train a multilingual model with LF-MMI is to combine the acoustic units from all languages and use a common denominator graph. The resulting model is either used as a feature extractor to train an acoustic model for the target language or directly fine-tuned. In this work, we propose a scalable approach to train the multilingual acoustic model using a typical multitask network for the LF-MMI framework. A set of language-dependent denominator graphs is used to compute the cost function. The proposed approach is evaluated under typical multilingual ASR tasks using GlobalPhone and BABEL datasets. Relative improvements up to 13.2% in WER are obtained when compared to the corresponding monolingual LF-MMI baselines. The implementation is made available as a part of the Kaldi speech recognition toolkit.