查詢結果分析
來源資料
相關文獻
- 以經正規化之字音聲紋圖進行語音比對
- 由字音聲紋圖擷取共振峰軌跡並用於限定語句式之語者驗證
- 基於機率線性鑑別分析之強健式語者驗證系統
- 建立語者韻母音色模型並應用於非限定語詞式之語者驗證
- 基於邊緣特徵之超音波與電腦斷層掃描影像對位技術
- Computation of Kullback-Leibler Distances for Score Normalization in Automatic Speaker Verification
- 語音壓縮標準G.723.1在C62X DSP上的設計
- Invariant Image Matching by Compacting and Moment Normalization
- 影響積差相關係數與α信度係數之因素
- 典型相關分析簡介
頁籤選單縮合
題 名 | 以經正規化之字音聲紋圖進行語音比對=Voice Matching Using Normalized Spectrograms |
---|---|
作 者 | 呂嘉穀; 耿良才; 蒲長恩; 蕭志濱; | 書刊名 | 前瞻科技與管理 |
卷 期 | 1:2 2011.11[民100.11] |
頁 次 | 頁85-96 |
分類號 | 312.85 |
關鍵詞 | 語者驗證; 聲紋圖; 正規化; 共振峰; 相關係數; Speaker verification; Spectrogram; Normalization; Formant; Correlation coefficient; |
語 文 | 中文(Chinese) |
中文摘要 | 語音是重要的生物特徵之一,可用於身分辨識之用。本論文中提出一個將字音聲紋圖加以正規化的方法。藉著正規化,我們可以消去說話快慢、音量大小、甚至於錄音裝置頻率響應之差異對聲紋圖所造成的影響,讓聲紋圖能夠單純的反映出語者在音色上的差異。我們藉著計算出兩個聲紋圖或是其導出圖形之間的相關係數,進行兩個字音之間相似程度的評量。我們經由一個七十人規模的實驗,以本方法來進行語者驗證。當只使用一個句子時做比對時,約可得到95%的正確率。而當我們使用到七個句子時,達到了99%的正確率。 |
英文摘要 | Voice is one of the primary biometrics, commonly used to identify a person. In this paper we present a method to normalize the spectrogram of a sound in a speech. Through this normalization process, we are able to remove the differences between two pieces of voice samples due to factors such as speed of utterance, loudness, and the frequency responses of the recording devices. As a result, we expect a normalized spectrogram will reflect mainly the tonal characteristics of its speaker. We use the correlation coefficient of the normalized spectrograms (and their two derivatives) to reflect the tonal similarity of the two voices. In the experiment, we collected voice samples of 36 males and 34 females. We then used the proposed method to conduct speaker verification. When only one sentence (around 8 to 10 Chinese characters) was used, we were able to achieve 95% accuracy. When we increased the number of sentences to 7, the accuracy rates exceed 99% for all three coefficients. |
本系統中英文摘要資訊取自各篇刊載內容。