计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
10期
14-17
,共4页
隐马尔可夫模型%语音识别%高效简约系统%声学模型拓扑结构%贝叶斯信息准则%粒群优化
隱馬爾可伕模型%語音識彆%高效簡約繫統%聲學模型拓撲結構%貝葉斯信息準則%粒群優化
은마이가부모형%어음식별%고효간약계통%성학모형탁복결구%패협사신식준칙%립군우화
Hidden Markov Model(HMM)%speech recognition%efficient and concise system%acoustic model topology%Bayesian Information Criterion(BIC)%Particle Swarm Optimization(PSO)
针对当前尚无建立简约高效语音识别系统标准方法的情形,提出了通过贝叶斯信息准则(Bayesian Information Criterion,BIC)中的权衡系数折中选择系统识别率与复杂度,利用改进的粒子群优化(Particle Swarm Optimization,PSO)算法优化声学模型拓扑结构,进而创建高效简约语音识别系统的新方法.TIDigits上的实验表明,与传统方法创建的同复杂度的基线系统相比,用该方法建立的新系统句子正确率提升了7.85%,与同识别率的基线系统相比,系统复杂度降低了51.4%,说明新系统能够以较低的复杂度获得较高的识别率.
針對噹前尚無建立簡約高效語音識彆繫統標準方法的情形,提齣瞭通過貝葉斯信息準則(Bayesian Information Criterion,BIC)中的權衡繫數摺中選擇繫統識彆率與複雜度,利用改進的粒子群優化(Particle Swarm Optimization,PSO)算法優化聲學模型拓撲結構,進而創建高效簡約語音識彆繫統的新方法.TIDigits上的實驗錶明,與傳統方法創建的同複雜度的基線繫統相比,用該方法建立的新繫統句子正確率提升瞭7.85%,與同識彆率的基線繫統相比,繫統複雜度降低瞭51.4%,說明新繫統能夠以較低的複雜度穫得較高的識彆率.
침대당전상무건립간약고효어음식별계통표준방법적정형,제출료통과패협사신식준칙(Bayesian Information Criterion,BIC)중적권형계수절중선택계통식별솔여복잡도,이용개진적입자군우화(Particle Swarm Optimization,PSO)산법우화성학모형탁복결구,진이창건고효간약어음식별계통적신방법.TIDigits상적실험표명,여전통방법창건적동복잡도적기선계통상비,용해방법건립적신계통구자정학솔제승료7.85%,여동식별솔적기선계통상비,계통복잡도강저료51.4%,설명신계통능구이교저적복잡도획득교고적식별솔.
Aiming at the current situation of lacking standard methods to construct efficient and concise speech recognition sys-tems, a new method to build this kind of systems is proposed, which involves determining the relative importance of the recogni-tion performance and system complexity through the value of the regularization coefficient in Bayesian Information Criterion (BIC)and optimizing acoustic model topologies using improved Particle Swarm Optimization(PSO)algorithm. Experiments on TIDigits corpus show that the new system constructed by using this method obtains 7.85%absolute increase in sentence correct rate compared to the baseline with the same complexity and built in the conventional way, and reduces 51.4%of system complexity compared to the baseline with the same recognition rate, which indicates that the new system is capable of obtaining higher recognition rate with lower system complexity.