Improved speech recognition method
for intelligent robot
2、Overview of speech recognition
Speech recognition has received more and more attention recently due to the important theoretical meaning and practical value [5 ]. Up to now, most speech recognition is based on conventional linear system theory, such as Hidden Markov Model (HMM) and Dynamic Time Warping(DTW) . With the deep study of speech recognition, it is found that speech signal is a complex nonlinear process. If the study of speech recognition wants to break through, nonlinear
-system theory method must be introduced to it. Recently, with the developmentof nonlinea-system theories such as artificial neural networks(ANN) , chaos and fractal, it is possible to apply these theories to speech recognition. Therefore, the study of this paper is based on ANN and chaos and fractal theories are introduced to process speech recognition.
Speech recognition is divided into two ways that are speaker dependent and speaker independent. Speaker dependent refers to the pronunciation model trained by a single person, the identification rate of the training person?sorders is high, while others’orders is in low identification rate or can’t be recognized. Speaker independent refers to the pronunciation model

改進(jìn)型智能機(jī)器人的語(yǔ)音識(shí)別方法
2、語(yǔ)音識(shí)別概述
最近，由于其重大的理論意義和實(shí)用價(jià)值，語(yǔ)音識(shí)別已經(jīng)受到越來(lái)越多的關(guān)注。到現(xiàn)在為止，多數(shù)的語(yǔ)音識(shí)別是基于傳統(tǒng)的線性系統(tǒng)理論，例如隱馬爾可夫模型和動(dòng)態(tài)時(shí)間規(guī)整技術(shù)。隨著語(yǔ)音識(shí)別的深度研究，研究者發(fā)現(xiàn)，語(yǔ)音信號(hào)是一個(gè)復(fù)雜的非線性過(guò)程，如果語(yǔ)音識(shí)別研究想要獲得突破，那么就必須引進(jìn)非線性系統(tǒng)理論方法。最近，隨著非線性系統(tǒng)理論的發(fā)展，如人工神經(jīng)網(wǎng)絡(luò)，混沌與分形，可能應(yīng)用這些理論到語(yǔ)音識(shí)別中。因此，本文的研究是在神經(jīng)網(wǎng)絡(luò)和混沌與分形理論的基礎(chǔ)上介紹了語(yǔ)音識(shí)別的過(guò)程。
語(yǔ)音識(shí)別可以劃分為獨(dú)立發(fā)聲式和非獨(dú)立發(fā)聲式兩種。非獨(dú)立發(fā)聲式是指發(fā)音模式是由單個(gè)人來(lái)進(jìn)行訓(xùn)練，其對(duì)訓(xùn)練人命令的識(shí)別速度很快，但它對(duì)與其他人的指令識(shí)別速度很慢，或者不能識(shí)別。獨(dú)立發(fā)聲式是指其發(fā)音模式是由不同年齡，不同性別，不同地域的人來(lái)進(jìn)行訓(xùn)練，它能識(shí)別一個(gè)群體的指令。一般地，由于用戶不需要操作訓(xùn)練，獨(dú)立發(fā)聲式系統(tǒng)得到了更廣泛的應(yīng)用。 所以，在獨(dú)立發(fā)聲式系統(tǒng)中，從語(yǔ)音信號(hào)中提取語(yǔ)音特征是語(yǔ)音識(shí)別系統(tǒng)的一個(gè)基本問(wèn)題。
語(yǔ)音識(shí)別包括訓(xùn)練和識(shí)別，我們可以把它看做一種模式化的識(shí)別任務(wù)。通常地，語(yǔ)音信號(hào)可以看作為一段通過(guò)隱馬爾可夫模型來(lái)表征的時(shí)間序列。通過(guò)這些特征提取，語(yǔ)音信號(hào)被轉(zhuǎn)化為特征向量并把它作為一種意見(jiàn)，在訓(xùn)練程序中，這些意見(jiàn)將反饋到HMM的模型參數(shù)估計(jì)中。這些參數(shù)包括意見(jiàn)和他們響應(yīng)狀態(tài)所對(duì)應(yīng)的概率密度函數(shù)，狀態(tài)間的轉(zhuǎn)移概率，等等。經(jīng)過(guò)參數(shù)估計(jì)以后，這個(gè)已訓(xùn)練模式就可以應(yīng)