Header menu link for other important links
Improving the Performance of Transformer Based Low Resource Speech Recognition for Indian Languages
, Shetty V.M., Sagaya Mary N J M.
Published in Institute of Electrical and Electronics Engineers Inc.
Volume: 2020-May
Pages: 8279 - 8283
The recent success of the Transformer based sequence-to-sequence framework for various Natural Language Processing tasks has motivated its application to Automatic Speech Recognition. In this work, we explore the application of Transformers on low resource Indian languages in a multilingual framework. We explore various methods to incorporate language information into a multilingual Transformer, i.e., (i) at the decoder, (ii) at the encoder. These methods include using language identity tokens or providing language information to the acoustic vectors. Language information to the acoustic vectors can be given in the form of one hot vector or by learning a language embedding. From our experiments, we observed that providing language identity always improved performance. The language embedding learned from our proposed approach, when added to the acoustic feature vector, gave the best result. The proposed approach with retraining gave 6% - 11% relative improvements in character error rates over the monolingual baseline. © 2020 IEEE.
About the journal
JournalData powered by TypesetICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
PublisherData powered by TypesetInstitute of Electrical and Electronics Engineers Inc.
Open AccessNo