外文翻译--基于仿生模式识别的非特定人连续语音识别系统(编辑修改稿)

外文翻译--基于仿生模式识别的非特定人连续语音识别系统(编辑修改稿)内容摘要：

, , , )]i i i iY f s s s x ， is a function with multivector input， one scalar quantity output． 2． Optimization method According to the ments in ,if there are many training samples, the neuron number will be very large thus reduce the recognition speed． In the case of learning several classes of samples, knowledge of the class membership of training samples is available. We use this information in a supervised training algorithm to reduce the work scales． When training class A， we looked the left training samples of the other 14 classes as class B． So there are 30 training samples in set 1 2 3 0: { , , }A A a a a … ，and 420 training samples in set 1 2 420: { , , }B B b b … ， b． Firstly select 3 samples from A, and we have a neuron：1 1 2 3Y =f [( , , , )]k k ka a a 0 1 _ 1 2 3, = f [ ( , , , ) ]A i k k k iA A Y a a a a ， where i= 1,2,… ， 30； 1 _ 1 2 3Y = f [ ( , , , ) ]B j k k k ja a a b， where j= 1,2,…420 ； 1_min(Y )BjV  ,we specify a value r ,0r1 .If 1_ *AiY r V ,removed ia from set A, thus we get a new set (1)A .We continue until the number of samples in set ()kA is () {}kA  ,then the training is ended, and the subNetwork of class A has a hidden layer of 1r neurons. V． Experiment Results A speech database consisting of 15 Chinese dish’s names was developed for the course of study. The length of each name is 4 Chinese words, that is to say, each sample of speech is a continuous string of 4 words, such as “yu xiang rou si”， “gong bao ji ding”， etc． It was organized into two sets： training set and test set. The speech signal is sampled at 16kHz and 16bit resolution． 第 4 页 Table 1． Experimental result at r of different values r Accuracy(%) MWN number The first option choice recognition rate The first two options choice recognition rate Training set Test set Training set Test set basic algorithm 448 132 126 115 110 96 93 84 65 52 44 450 utterances constitute the training set used to train the multiweights neuron works. The 450 ones belong to 10 speakers(5 males and 5 females) who are from different Chinese provinces. Each of the speakers uttered each of the word 3 times. The test set had a total of 539 utterances which involved another 4 speakers who uttered the 15 words arbitrarily． The tests made to evaluate the recognition system were carried out on different r from to with a step increment of experiment results atr of different values are shown in Table 1． Obviously， the works was able to achieve full recognition of training set at anyr ． From the experiments，it was found that  achieved hardly the same recognition rate as the Basic algorithm. In the mean time, the MWNs used in the works are much less than of the Basic algorithm. Table 2． Experiment results of BPR basic algorithm recognition method The first option choice recognition rate （ Test set） The first two option choice Recognition rate（ Test set） DTW % % HMM % % BPR Basic algorithm % % Experiments were also carried on to evaluate Continuous density hidden Markov models (CDHMM),Dynamic time warping(DTW) and Biomimetic pattern recognition(BPR) for speech recognition, emphasizing the performance of each method across decreasing amounts of training samples as well as requirement of train time. The CDHMM system was implemented with 5 states per and BaumWelch reestimation are used for training and recognition． The reference templates for DTW system are the 第 5 页 training samples themselves. Both the CDHMM and DTW technique are implemented using the。