Publication Details
Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages
Baskar Murali K. (DCGM FIT BUT)
Veselý Karel, Ing., Ph.D. (DCGM FIT BUT)
Grézl František, Ing., Ph.D. (DCGM FIT BUT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
Černocký Jan, prof. Dr. Ing. (DCGM FIT BUT)
Automatic speech recognition, Multilingual neural networks, Bidirectional Long Short Term Memory
The paper provides an analysis of automatic speech recognition systems (ASR) based on multilingual BLSTM, where we used multi-task training with separate classification layer for each language. The focus is on low resource languages, where only a limited amount of transcribed speech is available. In such scenario, we found it essential to train the ASR systems in a multilingual fashion and we report superior results obtained with pre-trained multilingual BLSTM on this task. The high resource languages are also taken into account and we show the importance of language richness for multilingual training. Next, we present the performance of this technique as a function of amount of target language data. The importance of including context information into BLSTM multilingual systems is also stressed, and we report increased resilience of large NNs to overtraining in case of multi-task training.
@INPROCEEDINGS{FITPUB11720, author = "Martin Karafi\'{a}t and K. Murali Baskar and Karel Vesel\'{y} and Franti\v{s}ek Gr\'{e}zl and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}", title = "Analysis of Multilingual BLSTM Acoustic Model on Low and High Resource Languages", pages = "5789--5793", booktitle = "Proceedings of ICASSP 2018", year = 2018, location = "Calgary, CA", publisher = "IEEE Signal Processing Society", ISBN = "978-1-5386-4658-8", doi = "10.1109/ICASSP.2018.8462083", language = "english", url = "https://www.fit.vut.cz/research/publication/11720" }