Hybrid CTC-Attention Network-Based End-to-End Speech Recognition System for Korean Language

In this study, an automatic end-to-end speech recognition system based on hybrid CTC-attention network for Korean language is proposed. Deep neural network/hidden Markov model (DNN/HMM)-based speech recognition system has driven dramatic improvement in this area. However, it is difficult for non-experts to develop speech recognition for new applications. End-to-end approaches have simplified speech recognition system into a single-network architecture. These approaches can develop speech recognition system that does not require expert knowledge. In this paper, we propose hybrid CTC-attention network as end-to-end speech recognition model for Korean language. This model effectively utilizes a CTC objective function during attention model training. This approach improves the performance in terms of speech recognition accuracy as well as training speed. In most languages, end-to-end speech recognition uses characters as output labels. However, for Korean, character-based end-to-end speech recognition is not an efficient approach because Korean language has 11,172 possible numbers of characters. The number is relatively large compared to other languages. For example, English has 26 characters, and Japanese has 50 characters. To address this problem, we utilize Korean 49 graphemes as output labels. Experimental result shows 10.02% character error rate (CER) when 740 hours of Korean training data are used.

The Language Use of a Bilingual Korean Teacher and Bilingual Korean Students in a Korean Heritage Classroom

Many Korean parents in the U.S. send their children to heritage Korean language schools so that they maintain and further develop Korean as they acquire English. It is, thus, worthwhile to investigate how a Korean teacher and Korean students (as emergent bilinguals) used Korean and English in a Korean heritage classroom. The chapter addresses two research questions: (1) How did the teacher use Korean and English to make her instruction comprehensible during discussions about multicultural children's literature? (2) To what extent were there differences in the two groups of students' (Korean-American and Korean immigrant) use of translanguaging in their oral responses? The findings show that the teacher uses both Korean and English to make her instruction comprehensible and to facilitate her students' participation in class discussions. The findings further reveal differences in the two groups of students' use of language in their oral responses to multicultural texts.