spce061a單片機(jī)的機(jī)器人設(shè)計(jì)-文庫(kù)吧資料
2025-07-05 19:39本頁(yè)面
【正文】 e 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 trained by persons of different age，sex and region，it can identify a group of persons’orders．Generally，speaker independent system ismorewidely used，since the user is not required to conduct the training．So extraction of speaker independent features from the speech signal is the fundamental problem of speaker recognition system．Speech recognition can be viewed as a pattern recognition task，which includes training and recognition．Generally，speech signal can be viewed as a time sequence and characterized by the powerful hidden Markov model (HMM)．Through the feature extraction，the speech signal is transferred into feature vectors and act asobservations．In the training procedure，these observationswill feed to estimate the model parameters of HMM．These parameters include probability density function for the observations and their corresponding states，transition probability between the states，etc．After the parameter estimation，the trained models can be used for recognition task．The input observations will be recognized as the resulted words and the accuracy can be evaluated． ３．Theory andmethodExtraction of speaker independent features from the speech signal is the fundamental problem of speaker recognition system．The standard methodology for solving this problem uses Linear Predictive Cepstral Coefficients(LPCC)and MelFrequency Cepstral Coefficient(MFCC)．Both these methods are linear procedures based on the assumption that speaker features have properties caused by the vocal tract resonances．These features form the basic spectral structure of the speech signal．However，the nonlinear information in speech signals is not easily extracted by the present feature extraction methodologies．So we use fractal dimension to measure non2linear speech turbulence．This paper investigates and implements speaker identification system using both traditional LPCC and nonlinear multiscaled fractal dimension feature extraction．3．3 Improved feature extractions methodConsidering the respective advantages on expressing speech signal of LPCC and fractal dimension,we mix both to be the feature signal，that is，fractal dimension denotes the self2similarity，periodicity and randomness of speech time wave shape，meanwhile LPCC feature is good for speech quality and high on identification rate．Due to ANN′s nonlinearity，selfadaptability，robust and selflearning such obvious advantages，its good classification and input2output reflection ability are suitable to resolve speech recognition problem．Due to the number of ANN input nodes being fixed，therefore time regularization is carried out to the feature parameter before inputted to the neural network[9]．In our experiments，LPCC and fractal dimension of each sample are need to get through the network of time regularization separately，LPCC is 4frame data(LPCC1,LPCC2,LPCC3,LPCC4，each frame parameter is 14D)，fractal dimension is regularized to be12frame data(FD1,FD2,…,FD12，each frame parameter is 1D)，so that the feature vector of each sample has 4*14+1*12=68D，the order is，the first 56 dimensions are LPCC，the rest 12 dimensions are fractal dimensions．Thus，such mixed feature parameter can show speech linear and nonlinear characteristics as well．４．Architectures and Features of ASRASR is a cutting edge technology that allows a puter or even a handheld PDA (Myers，2000) to identify words that are read aloud or spoken into any soundrecording device．The ultimate purpose of ASR technology is to allow 100% accuracy with all words that are intelligibly spoken by any person regardless of vocabulary size，background noise，or speaker variables (CSLU，2002)．However，most ASR engineers admit that the current accuracy level for a large vocabulary unit of speech (e．g．，the sentence) remains less than 90%． Dragon39。系統(tǒng)只用了單顆SPCE061A芯片來(lái)完成語(yǔ)音處理和控制功能，與專用的語(yǔ)音處理芯片相比，具有結(jié)構(gòu)簡(jiǎn)單、成本低、易實(shí)現(xiàn)的特點(diǎn)，并且凌陽(yáng)科技公司提供了豐富的C函數(shù)庫(kù)和語(yǔ)音處理函數(shù)庫(kù)，供調(diào)用，縮短了開(kāi)發(fā)周期。最常見(jiàn)的語(yǔ)音合成技術(shù)是將文本轉(zhuǎn)換為語(yǔ)音（TTS）。模式匹配，把輸入語(yǔ)音的特征參數(shù)與語(yǔ)音模型庫(kù)進(jìn)行比較分析，得到識(shí)別結(jié)果。特征提取，抽取反應(yīng)語(yǔ)音本質(zhì)的特征參數(shù)，形成特征矢量序列。在不同組指令中交換需要根據(jù)出發(fā)名稱，所以在識(shí)別狀態(tài)，要執(zhí)行動(dòng)作首先需要出發(fā)名稱，就是訓(xùn)練的第一條命令，然后可以識(shí)別第一組的其余四條命令。由于SPCE061A的FLASH存儲(chǔ)器只有32K，所以15條指令需要分組存放。當(dāng)一條指令被正確識(shí)別時(shí)會(huì)提示進(jìn)入下一條；如沒(méi)有被識(shí)別會(huì)要求重復(fù)該指令，直到正確識(shí)別為止。步驟三：打開(kāi)機(jī)器人的電源，進(jìn)行語(yǔ)音訓(xùn)練，訓(xùn)練過(guò)程按照下面進(jìn)行：按順序訓(xùn)練以下15條指令：“名稱”，“開(kāi)始”，“準(zhǔn)備”，“跳舞”，“再來(lái)一曲”，“開(kāi)始”，“向前走”，“倒退”，“右轉(zhuǎn)”，“左轉(zhuǎn)”，“準(zhǔn)備”，“向左瞄準(zhǔn)”，“向右瞄準(zhǔn)”，“發(fā)射”，“連續(xù)發(fā)射”。打開(kāi)機(jī)器人應(yīng)用實(shí)例程序，編譯、鏈接確認(rèn)沒(méi)有錯(cuò)誤。unsigned int BSR_SDModel[]；配合BSR_ExportSDWord(int CommandID)與BSR_ImportSDWord(int CommandID)函數(shù)使用，此數(shù)組的作用相當(dāng)于一個(gè)暫時(shí)的存儲(chǔ)區(qū)。BSR_ExportSDWord(int CommandID)使用函數(shù)庫(kù)時(shí)，會(huì)自動(dòng)創(chuàng)建一個(gè)100Word的數(shù)組BSR_SDModel[100]，可以把某條訓(xùn)練命令的特征模型數(shù)據(jù)導(dǎo)出到這個(gè)數(shù)組中。開(kāi)啟該功能后，IOA0和IOA1將發(fā)出每16ms電平變化一次的方波。 其它語(yǔ)音識(shí)別API介紹BSR_PauseR
環(huán)評(píng)公示相關(guān)推薦
鄂ICP備17016276號(hào)-1