母語與非母語英語之韻律模型建立

A prosody modeling approach to L1 and L2 English speech

陳韋帆(Wei-Fan Chen)

指導教授 ： 陳信宏

國立交通大學/電機學院/電信工程系所/碩士(2012年)

https://doi.org/10.6842/NCTU.2012.00623

摘要

本論文提出一個以音節為單位的韻律模型，其中包含了音節時間模型以及音節基頻軌跡模型。本論文考慮了若干會對這兩項韻律參數影響的因子，其中包括了重音類型、詞長、鄰近的停頓類型、音節組成的因素及韻律狀態等等。本論文使用一個疊代式的訓練法來建立此模型，並使用包含了母語與非母語英文語料的TWNAESOP語料庫。實驗數據顯示此模型能夠有效的建立起英語的韻律模型，與許多前人的研究結果符合；並且透過探討母語與非母語語者參數間的差別，我們得以從數據上得知兩者間韻律上的差異。

關鍵字

韻律模型 ； 非母語英文 ； 音節時間模型 ； 音節基頻軌跡模型

並列摘要

In this thesis, a statistical prosody modeling approach for L1 and L2 English speeches is proposed. The study focuses on the modeling of two prosodic-acoustic features: syllable duration and log-pitch contour. Several major affecting factors (AFs) that influence the variations of these two features are considered. They include lexical stress, word length, nearby break type, phonemic constituent of syllable, and prosodic state. A sequential optimization procedure is adopted to automatically train the two models from the TWNAESOP corpus recorded in Taiwan. The corpus contained both L1 and L2 English speeches. Experimental results showed that most AFs estimated agreed well with our prior linguistic knowledge. The differences in the prosody of L1 and L2 speeches were explored.

並列關鍵字

prosody modeling ； L2 Englisg speech ； duration modeling ； pitch contour modeling

參考文獻

【1】 Visceglia, Tanya, Tseng, Chiu-yu, Kondo, Mariki, Meng, Helen and Sagisaki, Yoshinori, “Phonetic aspects of content design in AESOP (Asian English Speech cOrpus Project, Oriental COCOSDA,” Beijing, China, 2009.

【2】 Chiu-yu Tseng, “Phonotactic and discourse aspects of content design in AESOP (Asian English Speech cOrpus Project),” Oriental-COCOSDA, Hsinchu, Taiwan, 2011.

【3】 C. Y. Tseng, and T. Visceglia, “AESOP (Asian English Speech Corpus Project) and TWNAESOP,” Invited keynote speech, Int. Conf. and Workshop on TEFL & Applied Linguistics, March, 2010.

【4】 Visceglia, Tanya, Tseng, Chiu-yu, Su, Zhao-yu and Huang, Chi-Feng, “Realization of English Narrow Focus by L1 English and L1 Taiwan Mandarin Speakers”, The 7th International Congress of Phonetic Sciences. Hong Kong, China, 2011.

【5】 Tseng, Chiu-yu, Su, Zhao-yu, Huang, Chi-Feng and Visceglia, Tanya, “An Initial Investigation of L1 and L2 Discourse Speech Planning in English,” The 7th International Symposium on Chinese Spoken Language Processing (ISCSLP) 55-59. Tainan/Sun Moon Lake, Taiwan, 2010.