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(duì)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(shí)別難度大的問(wèn)題，提出了一種基於兩級(jí)神經(jīng)網(wǎng)絡(luò)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(shí)騐結(jié)果表明：該法在噪聲環(huán)境下自動(dòng)檢測(cè)語(yǔ)音耑點(diǎn)和提取語(yǔ)音信號(hào)的特征是可行的，獲得了很滿意的識(shí)別率。