頁籤選單縮合
題名 | A Phonetic Labeling Method for Mat Database Processing=處理MAT語音資籵庫的聲學標音方法 |
---|---|
作者 | 王小川; 邱榮樑; 莊向凱; 黃儀芬; Wang, Hsiao-chuan; Chiou, Rong-liang; Chuang, Shiang-kai; Huang, Yi-fen; |
期刊 | 中國工程學刊 |
出版日期 | 19990900 |
卷期 | 22:5 1999.09[民88.09] |
頁次 | 頁529-534 |
分類號 | 312.23 |
語文 | eng |
關鍵詞 | 聲學標音; 國語語音資料庫; 語音訊號分割; Phonetic labeling; Mandarin speech database; Speech signal segmentation; |
中文摘要 | 本文提出一個半自動化的聲學標音方法,用以處理MAT國語語音資料庫。MAT國語 語音資料係通過電話網路收集,每個語音已經轉譯成中文字及拼音符號。所提出之聲學標音 方法會在語音訊號波形上標示出音節及次音節之邊界,在分割的音節上標示聲學符號。語音 訊號之分割是採用隱藏式馬可夫模型與維特比解碼程序,音節分割之正確性,係由音節長度 量測及音節特徵參數與其對應模型之間距離量測來判斷。實驗結果顯示,在 16ms 之容許誤 差範圍內,所提之聲學標音方法可以得到約 90% 之精確度。 |
英文摘要 | This paper presents a semi-automatic phonetic labeling method for processing in the MAT (Mandarin across Taiwan) speech database. MAT speech data are collected through the telephone networks. Each utterance has been transcribed into Chinese characters and Pinyin symbols. The proposed phonetic labeling method will mark the syllable and sub-syllable boundaries in an utterance. Phonetic symbols are assigned to each segmented syllable. The segmentation process is accomplished by using hidden Markov modeling (HMM) and Viterbi decoding. The accuracy of syllable segmentation is detected by measuring the syllable length and the distance of a syllable from its state models. The experimental results show that the proposed labeling method can achieve segmentation accuracy around go% for an allowed tolerance of lG ms. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。