@inproceedings{24f0911bf59d4990a798b696dab686fe,
title = "探究語言模型合併策略應用於中英文語碼轉換語音辨識",
abstract = "Code-switching (CS) speech is a common language phenomenon in multilingual societies. For example, the official language in Taiwan is Mandarin Chinese, but the daily conversations of the ordinary populace are often mingled with English words, phrases or sentences. It is generally agreed that transcription of CS speech remains an important challenge for the current development of automatic speech recognition (ASR). One of the straightforward and feasible ways to promote the efficacy of CS ASR is to improve the language model (LM) involved in ASR. Given these observations, we put forward disparate strategies that conduct combination of various language models at different stages of the ASR process. Our experimental configuration consists of two CS (i.e., mixing of Mandarin Chinese and English) language models and one monolingual (i.e. Mandarin Chinese) language models, where the two CS language models are domain-specific and the monolingual language model is trained on a general text collection. Through the language model combination at different stages of the ASR process, we purport to know if the ASR system could integrate the strengths of various language models to achieve improved performance across different tasks. More specifically, three strategies for combining language models are investigated, namely simple N-gram language model combination, decoding graph combination and word lattice combination. A series of ASR experiments conduct on CS speech corpora complied from different industrial application scenarios have confirm the utility of the aforementioned LM combination strategies.",
keywords = "automatic speech recognition, code-switching, decoding graph, language model, word lattice",
author = "Lin, {Wei Ting} and Berlin Chen",
note = "Publisher Copyright: {\textcopyright} ROCLING 2020.All rights reserved.; 32nd Conference on Computational Linguistics and Speech Processing, ROCLING 2020 ; Conference date: 24-09-2020 Through 26-09-2020",
year = "2020",
language = "繁體中文",
series = "ROCLING 2020 - 32nd Conference on Computational Linguistics and Speech Processing",
publisher = "The Association for Computational Linguistics and Chinese Language Processing (ACLCLP)",
pages = "346--358",
editor = "Jenq-Haur Wang and Ying-Hui Lai and Lung-Hao Lee and Kuan-Yu Chen and Hung-Yi Lee and Chi-Chun Lee and Syu-Siang Wang and Hen-Hsen Huang and Chuan-Ming Liu",
booktitle = "ROCLING 2020 - 32nd Conference on Computational Linguistics and Speech Processing",
}