Search

Supplementary materials for manuscript

Analysis code

Production data from the experiment

Stimuli for eliciting production data

This study examines phonetic transfer between Bengali and English in a group of proficient bilingual speakers in India. We measure spectral properties (F1 and F2) of two English vowels, [ʌ] and [æ], to ascertain if L1 influence on L2 increases during mixed-language use, relative to a participant’s unilingual baseline production of L2. Mixed-language data is elicited in two switching paradigms: code-switching and cued picture-naming.

Language Identification (LID), a recommended initial step to Automatic Speech Recognition (ASR), is used to detect a spoken language from audio specimens. In state-of-the-art systems capable of multilingual speech processing, however, users have to explicitly set one or more languages before using them. LID, therefore, plays a very important role in situations where ASR based systems cannot parse the uttered language in multilingual contexts causing failure in speech recognition. We propose an attention based convolutional recurrent neural network (CRNN with Attention) that works on Mel-frequency Cepstral Coefficient (MFCC) features of audio specimens. Additionally, we reproduce some state-of-the-art approaches, namely Convolutional Neural Network (CNN) and Convolutional Recurrent Neural Network (CRNN), and compare them to our proposed method. We performed extensive evaluation on thirteen different Indian languages and our model achieves classification accuracy over 98%. Our LID model is robust to noise and provides 91.2% accuracy in a noisy scenario. The proposed model is easily extensible to new languages.