Research on continuous speech recognition with small vocabulary based on biomimetic pattern recognition

Based on biomimetic pattern recognition theory, we proposed a novel speaker-independent continuous speech keyword-spotting algorithm. Without endpoint detection and division, we can get the minimum distance curve between continuous speech samples and every keyword-training net through the dynamic searching to the feature-extracted continuous speech. Then we can count the number of the keywords by investigating the vale-value and the numbers of the vales in the curve. Experiments of small vocabulary continuous speech with various speaking rate have got good recognition results and proved the validity of the algorithm.

Pattern Recognition With Weighted Complex Networks

In this paper we introduce a weighted complex networks model to investigate and recognize structures of patterns. The regular treating in pattern recognition models is to describe each pattern as a high-dimensional vector which however is insufficient to express the structural information. Thus, a number of methods are developed to extract the structural information, such as different feature extraction algorithms used in pre-processing steps, or the local receptive fields in convolutional networks. In our model, each pattern is attributed to a weighted complex network, whose topology represents the structure of that pattern. Based upon the training samples, we get several prototypal complex networks which could stand for the general structural characteristics of patterns in different categories. We use these prototypal networks to recognize the unknown patterns. It is an attempt to use complex networks in pattern recognition, and our result shows the potential for real-world pattern recognition. A spatial parameter is introduced to get the optimal recognition accuracy, and it remains constant insensitive to the amount of training samples. We have discussed the interesting properties of the prototypal networks. An approximate linear relation is found between the strength and color of vertexes, in which we could compare the structural difference between each category. We have visualized these prototypal networks to show that their topology indeed represents the common characteristics of patterns. We have also shown that the asymmetric strength distribution in these prototypal networks brings high robustness for recognition. Our study may cast a light on understanding the mechanism of the biologic neuronal systems in object recognition as well.

Seasonal changes in the trade-off among fig-supported wasps and viable seeds in figs and their evolutionary implications

What the real trade-off is among fig-supported wasps and the viable seeds of figs is heatedly debated in the studies of fig/fig wasp mutualism. In the present study, we collected wasp offspring (galls) and the viable seeds of premature fruits, and determined the foundress number in receptive fruits and all the types of wasps supported by Ficus racemosa L. during both the rainy and dry seasons in Xishuangbanna, China. The data show that the galls were positively correlated with viable seeds (n=32;r=0.74; P < 0.001) when the proportion of vacant female flowers (PVFF) was high, in April (68.0%), and were negatively correlated with viable seeds (n=48;r=-0.59; P < 0.05) when PVFF were limited (PVFF 42.6%) during a colder month (January). The mean foundress number per fruit during the colder months is significantly lower than during the warmer months (F-5,F-603 = 27.9; P < 0.001) and pollinator wasps can live longer during the colder months, During the colder months, the proportions of non-pollinators and wasp offspring are higher than those found during other months, whereas the proportion of viable seeds is not different compared with that of other months. Non-pollinator wasps tend to oviposit the female flowers that have been oviposited by pollinator wasps. The non-pollinators only negatively affect pollinator wasps and there is no obvious negative effect of non-pollinator wasps on viable seeds, so ovipositing by non-pollinator wasps will not result in the extinction of the figs during the process of evolution. The results of the present study indicate that figs can allow less foundresses to be in fruit cavities when PVFF are limited, which provides supporting evidence for the previous assumption that the plants have developed a mechanism to maintain a stable system because of the conflicts between the parties involved.

A speaker-independent continuous speech recognition system using biomimetic pattern recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology (HMMs, or Hidden Markov models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic pattern recognition (BPR) in recognizing some mandarin continuous speech in a speaker-independent manner. A speech database was developed for the course of study. The vocabulary of the database consists of 15 Chinese dish's names, the length of each name is 4 Chinese words. Neural networks (NNs) based on Multi-weight neuron (MWN) model are used to train and recognize the speech sounds. The number of MWN was investigated to achieve the optimal performance of the NNs-based BPR. This system, which is based on BPR and can carry out real time recognition reaches a recognition rate of 98.14% for the first option and 99.81% for the first two options to the persons from different provinces of China speaking common Chinese speech. Experiments were also carried on to evaluate Continuous density hidden Markov models (CDHMM), Dynamic time warping (DTW) and BPR for speech recognition. The Experiment results show that BPR outperforms CDHMM and DTW especially in the cases of samples of a finite size.

Biomimetic pattern recognition for speaker-independent speech recognition

In speaker-independent speech recognition, the disadvantage of the most diffused technology ( Hidden Markov Models) is not only the need of many more training samples, but also long train time requirement. This paper describes the use of Biomimetic Pattern Recognition (BPR) in recognizing some Mandarin Speech in a speaker-independent manner. The vocabulary of the system consists of 15 Chinese dish's names. Neural networks based on Multi-Weight Neuron (MWN) model are used to train and recognize the speech sounds. Experimental results are presented to show that the system, which can carry out real time recognition of the persons from different provinces speaking common Chinese speech, outperforms HMMs especially in the cases of samples of a finite size.

金钱启动与道德的关系及道德认同的调节

In this article, we begin from the research about how money influences the behavior of people, and try to discuss how money influences people's moral judgment on the five degrees of morality (harm/care, fairness/reciprocal, loyalty/in-group, authority/respect, purity/sanctity). Meanwhile, we try to discuss whether the money priming is based on the mechanism of competition priming. Besides that, we want to find out whether moral identification and positive vocabulary could rescue the change of moral judgment after money priming. The money priming in this research is based on picture priming and syntax priming; the competition priming and moral identification priming are based on imagination priming. We chose the undergraduate, graduate student and adult as sample, combined the scale investigation with computer based experiment. This research contains five standard case experiments, which form three. Based on all the research above, we have some conclusions: 1. Money priming has impacts on moral judgment, which are not consistent on different degree of morality. But the total effect of money priming is that it changes moral judgment to a worse state. 2. Money priming is not complete competition priming, but social value orientation (including competition orientation) could mediate the influence of money priming on moral judgment. Generally, people with personal orientation or competition orientation could be influenced more easily by money priming. 3. After money priming, the moral judgment could be influence by moral identification and positive vocabulary. In all, both the moral judgment and positive vocabulary could make the moral judgment to a better state. But the function of them may be different, moral identification is more related to moral cognition and positive vocabulary is more related to moral emotional regulation. This research is based on priming method, and supports the money influence on psychology, the concept of morality and moral identification with experimental evidence. Also this research discusses the measurement of morality.

汉语婴儿对早期词汇的理解与表达

Whether Mandarin is a verb-friendly language for young word learners or not is a hotly debated issue. Researches on children's word learning were either naturalistic study or experimental study, and they were from cross-cultural perspective. This study tries to examine the noun/verb proportion in Mandarin infants, from a longitudinal perspective; it also examines how Mandarin infants understand their first nouns and verbs using both naturalistic study and experimental study. The results of this research are: 1） According to the results of CDI test, Mandarin infants of 18 month old could say more verbs than nouns significantly; while 24 month-olds could say more nouns than verbs significantly. 2） According to the results of CDI test, Mandarin infants’ verb/noun proportion was higher in 18 month old than in 24 month old. This means that the relative advantage of verb learning may be easier to show up in infants younger than 2 years old. 3） The total vocabulary of 18 month-olds was positively correlated with the Mean Length of Utterances(MLU) of 24 month-olds. The MLU of 24 month olds was positively correlated with the verbs of 18 month-olds. 4） Only 24 month-old could succeed in our IPLP study and showed “true” understanding to their familiar words. 14- and 18- month-olds watch the target side and non-target side randomly. 5） According to the results of IPLP study, the infants could understand nouns better than verbs. Both female and male infants understood nouns better than verbs, but females seemed to have stronger tendency to watch the object-same side in both noun and verb condition. 6） According to the results of parents’ reports, all the infants in 3 age groups could understand verbs as well as nouns, and they are quite familiar with those words. However, IPLP study results showed that these infants understood nouns better than verbs. 7） In IPLP study, less than 50% of the Mandarin infants watch the target side of verbs longer than the non-target side (action-same response). However, the AS responses appear more frequently in verb condition than in noun condition among 24-month-olds.