查詢結果分析
來源資料
相關文獻
- A Study of Mandarin Audio-Visual Emotional Speech Recognition
- 慢性阻塞性肺部疾病患者肺功能狀態與中醫證型及舌診影像科學化研究之關係
- A Model-Based Technique for Flaw Detection, Sizing, and Reconstruction
- 以連續型隱藏式馬可夫模型來計算中文簽名之動態相似度值
- An Overview of RNN-Based Mandarin Speech Recognition Approaches
- 撓骨動脈信號特徵之自動擷取系統
- 以色彩、紋理、和外形為內容之影像擷取方法
- 高效能多媒體文件分類法則之研究
- 基於VQ/HMM之國語文句翻語音中音節音長與振幅參數產生之方法
- An Overview of Mandarin-Speech Tone Recognition
頁籤選單縮合
題名 | A Study of Mandarin Audio-Visual Emotional Speech Recognition=具有情緒之中文聽視覺語音辨識系統之研究 |
---|---|
作者 | 廖文淵; | 書刊名 | 德霖學報 |
卷期 | 24 2010.08[民99.08] |
頁次 | 頁225-236 |
分類號 | 312.85 |
關鍵詞 | 具有情緒之中文聽視覺語音辨識系統; 特徵擷取; 隱藏式馬可夫模型; 離散權值KNN分類器; WD-KNN; Emotional audio-visual speech recognition; Feature extraction; Hidden Markov model; Weighted-discrete KNN; |
語文 | 英文(English) |
中文摘要 | 近幾年來,語音視覺特徵用於輔助語音辨識的方法,已經發展出來,並具有良好的效能。本論 文提出一個可以辨識具有情緒的語音視覺辨識系統。在所建置的系統中,我們擷取聽視覺特徵作為 辨識器分類的輸入參數,其中視覺特徵在我們的系統中是非常重要的辨識線索。在後端的辨識器則 利用離散權值KNN 分類器作為辨識系統的基礎。我們使用包括高斯混合模型與隱藏式馬可夫模型 等辨識器,來比較及驗證所提出的WD-KNN 分類器。實驗結果顯示使用WD-KNN 分類器可以在 中文語音具有情緒的狀況下獲得比其他分類器較佳的辨識結果。 |
英文摘要 | Automatic speech recognition (ASR) by machine has been a goal and an attractive research area for past several decades. In recent years, there has been growing attractive research topic for overcoming certain audio-only recognition problems. This paper presents a Mandarin audio-visual recognition system dealing with emotional speech signal. In the proposed approach, we extract the visual features of the lips. These features are very important to the recognition system especially in noisy condition or with emotional effects. In this recognition system, we propose to use the weighted-discrete KNN as the classifier and compare the results with two popular classifiers, the GMM and HMM, and evaluate their performance by applying to an emotional Mandarin audio-visual speech corpus. The experimental results of different classifiers at various emotions are presented. The results show that using the WD-KNN classifier yields better recognition accuracy than other classifiers for the used Mandarin speech corpus. |
本系統之摘要資訊系依該期刊論文摘要之資訊為主。