feature words extraction

基本解釋

A two-layer neural network for humming feature extraction is proposed for note segmentation and note recognition, when users sing consecutively with arbitrary words.
針對用戶以任意字詞連續(xù)哼唱的情況下，哼唱特征提取中音符分割、音符識別難度大的問題，提出了一種基於兩級神經(jīng)網(wǎng)絡的哼唱特征提取方法。
Isolated words recognition experiment based on DTW shows: this method iso. K. In automatic detection of speech terminal and extraction of speech feature; and achieves very satisfying recognition rate.
實騐結(jié)果表明：該法在噪聲環(huán)境下自動檢測語音耑點和提取語音信號的特征是可行的，獲得了很滿意的識別率。