Helium speech enhancement based on linear predictive coding 基于線性預(yù)測(cè)模型的氦語(yǔ)音增強(qiáng)算法研究
Linear predictive code lpc 線性預(yù)測(cè)編碼
Linear predictive code lp 線性預(yù)測(cè)編碼
A study on noisy speech recognition linear predictive coding prediction error 一種噪聲環(huán)境下的語(yǔ)音識(shí)別方法線性預(yù)測(cè)誤差法的研究
One - sided autocorrelation sequence ; linear predictive coding ; cepstrum ; dynamic time warping 單邊自相關(guān)序列線性預(yù)測(cè)編碼倒譜動(dòng)態(tài)時(shí)間規(guī)正
Linear predictive coding ; lpc prediction error ; cepstrum ; dynamic time warping 線性預(yù)測(cè)編碼lpc lpcpe線性預(yù)測(cè)誤差倒譜動(dòng)態(tài)時(shí)軸彎曲或動(dòng)態(tài)時(shí)間規(guī)正dtw
This thesis tries to update the cmdsr system to achieve the characters below : real - time , better robust , higher recognition rate , non - special - man . considering the disadvantages of traditional improved spectrum subtraction speech enhancement , this thesis proposes the theory of fuzzy spectrum subtraction based on the fuzzy theory and improved spectrum subtraction speech enhancement ; as for the difficulties of detecting the endpoint of speech signal , the thesis gives the table of initial and the improved parameters , with which we can confirm the endpoints of mandarin digit speech ; the thesis puts forward two - level digit real - time speech recognition system , the first level is based on discrete hidden markov model which is linear predictive coding cepstrum ( lpcc ) and difference linear predictive coding cepstrum ( dlpcc ) , the second level is based on formant parameters ; as for the realization of hardware , the thesis depicts the realization of every part of cmdsr based on the tms320vc5402 in detail ; as for the development of software , the thesis gives the software design flow chart of cmdsr , simulates the basic theory with matlab language and gives the simulation results 針對(duì)傳統(tǒng)的“改進(jìn)譜相減法語(yǔ)音增強(qiáng)”參數(shù)設(shè)定單一、環(huán)境適應(yīng)能力差的缺點(diǎn),提出了一種利用模糊理論和“改進(jìn)的譜相減法”結(jié)合的“模糊譜相減法語(yǔ)音增強(qiáng)” ;針對(duì)語(yǔ)音信號(hào)端點(diǎn)檢測(cè)困難的特點(diǎn),通過(guò)matlab仿真試驗(yàn),給出了能夠準(zhǔn)確確定數(shù)碼語(yǔ)音端點(diǎn)的初始和改進(jìn)參數(shù)表;提出了利用基于線性預(yù)測(cè)編碼倒譜參數(shù)和差分線性預(yù)測(cè)編碼倒譜參數(shù)相結(jié)合的離散隱含馬爾可夫模型進(jìn)行第一級(jí)識(shí)別、利用共振峰參數(shù)進(jìn)行第二級(jí)識(shí)別的兩級(jí)漢語(yǔ)數(shù)碼語(yǔ)音識(shí)別系統(tǒng),在保證系統(tǒng)實(shí)時(shí)性的同時(shí),實(shí)現(xiàn)連接漢語(yǔ)數(shù)碼語(yǔ)音識(shí)別系統(tǒng)識(shí)別率的提高;在硬件實(shí)現(xiàn)上,詳細(xì)闡述了基于tms320vc5402的連接漢語(yǔ)數(shù)碼語(yǔ)音識(shí)別系統(tǒng)各部分硬件設(shè)計(jì);在軟件開(kāi)發(fā)上,給出了連接漢語(yǔ)數(shù)碼語(yǔ)音識(shí)別的軟件設(shè)計(jì)各部分的流程圖,并對(duì)各部分進(jìn)行了matlab仿真,并給出了仿真結(jié)果。