CONF Tong_INTERSPEECH_2018/IDIAP Fast Language Adaptation Using Phonological Information Tong, Sibo Garner, Philip N. Bourlard, Hervé connectionist temporal classification (ctc) crosslingual adaptation dnn-based speech recognition Phonological features EXTERNAL https://publications.idiap.ch/attachments/papers/2018/Tong_INTERSPEECH_2018.pdf PUBLIC Proceedings of Interspeech 2018 Hyderabad, INDIA 2018 2459-2463 2308-457X 978-1-5108-7221-9 10.21437/Interspeech.2018-1990 doi Phoneme-based multilingual connectionist temporal classification (CTC) model is easily extensible to a new language by concatenating parameters of the new phonemes to the output layer. In the present paper, we improve cross-lingual adaptation in the context of phoneme-based CTC models by using phonological information. A universal (IPA) phoneme classifier is first trained on phonological features generated from a phonological attribute detector. When adapting the multilingual CTC to a new, never seen, language, phonological attributes of the unseen phonemes are derived based on phonology and fed into the phoneme classifier. Posteriors given by the classifier are used to initialize the parameters of the unseen phonemes when extending the multilingual CTC output layer to the target language. Adaptation experiments show that the proposed initialization approaches further improve the cross-lingual adaptation on CTC models and yield significant improvements over Deep Neural Network / Hidden Markov Model (DNN/HMM)-based adaptation using limited data.