Shared-hidden-layer Deep Neural Network for Under-resourced Language the Content

Devin Hoesen (Institut Teknologi Bandung)
Dessi Puji Lestari (Institut Teknologi Bandung)
Dwi Hendratmo Widyantoro (Institut Teknologi Bandung)

TELKOMNIKA (Telecommunication Computing Electronics and Control)
Vol 16, No 3: June 2018

Training speech recognizer with under-resourced language data still proves difficult. Indonesian language is considered under-resourced because the lack of a standard speech corpus, text corpus, and dictionary. In this research, the efficacy of augmenting limited Indonesian speech training data with highly-resourced-language training data, such as English, to train Indonesian speech recognizer was analyzed. The training was performed in form of shared-hidden-layer deep-neural-network (SHL-DNN) training. An SHL-DNN has language-independent hidden layers and can be pre-trained and trained using multilingual training data without any difference with a monolingual deep neural network. The SHL-DNN using Indonesian and English speech training data proved effective for decreasing word error rate (WER) in decoding Indonesian dictated-speech by achieving 3.82% absolute decrease compared to a monolingual Indonesian hidden Markov model using Gaussian mixture model emission (GMM-HMM). The case was confirmed when the SHL-DNN was also employed to decode Indonesian spontaneous-speech by achieving 4.19% absolute WER decrease.