需要金幣： 1000 個金幣 |
資料包括：完整論文，開題報告，任務(wù)書 |  |
 |
| 轉(zhuǎn)換比率：金額 X 10=金幣數(shù)量， 例100元=1000金幣 | 論文字?jǐn)?shù)：18975 |  | |
| 折扣與優(yōu)惠：團(tuán)購最低可5折優(yōu)惠 - 了解詳情 | 論文格式：Word格式(*.doc) |  |
摘要:語音識別技術(shù)是一門交叉學(xué)科，正逐步成為信息技術(shù)中人機(jī)交互的關(guān)鍵技術(shù)。通過語音傳遞信息是人類最重要、最有效、最常用和最方便的交換信息形式。本文是對特定人連續(xù)電話號碼的語音進(jìn)行識別。本系統(tǒng)中采用基于短時平均幅度和過零率的雙門限法進(jìn)行語音端點檢測；用充分考慮了人耳聽覺特性的Mel頻率倒譜參數(shù)(MFCC)作為語音信號特征矢量，采用隱馬爾可夫模型(HMM)算法來完成語音模板的訓(xùn)練和語音識別的任務(wù)。對電話號碼語音識別系統(tǒng)進(jìn)行驗證，實驗室環(huán)境現(xiàn)場識別100組隨機(jī)電話號碼，其中全部識別正確的有22組。通過對0~9這10個數(shù)字分別統(tǒng)計，最低識別率為72.84%。 關(guān)鍵詞：語音識別；端點檢測；MFCC；HMM
Abstract:The speech recognition is a cross-discipline, and is gradually becoming the key-technology of human-machine interation in information technology. Transmission of information through the voice of humanity’s most important, most effective,most popular and most convenient form of exchange of information. This paper presents the speaker-dependent continuous speech recognition of telephone numbers. This system is based on SAM-SAZR(Short-time Average Magnitude and Short-time Average Zero-crossing Rate). The system adopts Mel Frequency Cepstrum Coefficient (MFCC), which considers fully sense of hearing characteristic, as voice signal eigenvector. The discrete hidden markov model(HMM)is adopted to train and recognize the speech signal. Experiments are done to validate the telephone voice recognition simulation, on-site to identify 100 groups of random numbers, which identify all right with 22 groups. Through the 10 Numbers 0~9 were statistics, minimum recognition rate is 72.84%. Key words：Voice Signal, Endpoint detection, MFCC,HMM
本課題基于Matlab仿真軟件實現(xiàn)特定人電話號碼連續(xù)語音識別系統(tǒng)的設(shè)計。首先，利用Windows自帶的錄音設(shè)備進(jìn)行錄音，完成了對模型庫的訓(xùn)練，建立了0~9這個10個數(shù)字的模型建立。其次，通過對語音識別的基本原理和模式識別基本原理的學(xué)習(xí)，更好的理解了語音識別的過程。本文采用了MFCC特征提取和HMM識別算法，完成了對11位和12位電話號碼的識別。因為手機(jī)號碼是11位，而固定電話的位數(shù)是區(qū)號+8位號碼，例如常州的區(qū)號為0519，而南京的區(qū)號025。當(dāng)捕捉到的電話號碼不足11或者超過12位時，系統(tǒng)會給出選擇是否繼續(xù)錄音。
|
