Mehr lesen
The book presents current research and developments in multilingual speech recognition. The author presents a Multilingual Phone Recognition System (Multi-PRS), developed using a common multilingual phone-set derived from the International Phonetic Alphabets (IPA) based transcription of six Indian languages - Kannada, Telugu, Bengali, Odia, Urdu, and Assamese. The author shows how the performance of Multi-PRS can be improved using tandem features. The book compares Monolingual Phone Recognition Systems (Mono-PRS) versus Multi-PRS and baseline versus tandem system. Methods are proposed to predict Articulatory Features (AFs) from spectral features using Deep Neural Networks (DNN). Multitask learning is explored to improve the prediction accuracy of AFs. Then, the AFs are explored to improve the performance of Multi-PRS using lattice rescoring method of combination and tandem method of combination. The author goes on to develop and evaluate the Language Identification followed by Monolingual phone recognition (LID-Mono) and common multilingual phone-set based multilingual phone recognition systems.
Über den Autor / die Autorin
Dr. Manjunath K E received his PhD in multilingual speech recognition from International Institute of Information Technology, Bangalore, India, and his MS in automatic speech recognition from Indian Institute of Technology, Kharagpur, India. Currently, he works as Scientist at U R Rao Satellite Centre, Indian Space Research Organisation (ISRO). He has published in several international conferences and journals. He has co-authored the book "Speech recognition using Articulatory and Excitation Source Features" (Springer 2017).
