本文選題：多窗譜估計(jì) + 伽馬通濾波器組��； 參考：《浙江工業(yè)大學(xué)學(xué)報(bào)》2017年06期

【摘要】：用多窗譜估計(jì)和伽馬通濾波改進(jìn)經(jīng)典的梅爾倒譜特征(MFCC)的識(shí)別性能,并與delta特征相結(jié)合,提出了一種基于加權(quán)參數(shù)設(shè)置策略的混合特征話者識(shí)別算法.該算法解決了梅爾倒譜系數(shù)方差過(guò)大、聽(tīng)覺(jué)特征不明顯及話者識(shí)別算法特征單一的問(wèn)題.仿真結(jié)果表明:與MFCC和線性預(yù)測(cè)的提取方法相比,該算法魯棒性能更優(yōu),對(duì)不同噪聲環(huán)境的適應(yīng)性更好.
[Abstract]:In this paper , the recognition performance of classical Mel cepstrum feature ( MFCC ) is improved by multi - window spectral estimation and gamma filtering and combined with delta feature . The algorithm solves the problem that the variance of the Mel cepstrum coefficient is too large , the auditory characteristic is not obvious and the speech recognition algorithm is single . The simulation results show that the robustness of the algorithm is better than that of MFCC and linear prediction , and the adaptability of the algorithm is better for different noise environments .

【作者單位】： 浙江工業(yè)大學(xué)信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金資助項(xiàng)目(61471322,61402416)
【分類(lèi)號(hào)】：TN912.3

【相似文獻(xiàn)】

相關(guān)期刊論文 前2條

1 徐自勵(lì);華偉;王一揚(yáng);;多窗譜估計(jì)法估計(jì)相干函數(shù)的雙端語(yǔ)音檢測(cè)[J];通信技術(shù);2007年05期

2 吳紅衛(wèi);吳鎮(zhèn)揚(yáng);趙鶴鳴;趙力;;多正弦窗譜估計(jì)的性能分析[J];信號(hào)處理;2007年06期

，

本文編號(hào)：1856172