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.

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.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

Continuous speech recognition based on ICA and geometrical learning

We investigate the use of independent component analysis (ICA) for speech feature extraction in digits speech recognition systems. We observe that this may be true for recognition tasks based on Geometrical Learning with little training data. In contrast to image processing, phase information is not essential for digits speech recognition. We therefore propose a new scheme that shows how the phase sensitivity can be removed by using an analytical description of the ICA-adapted basis functions. Furthermore, since the basis functions are not shift invariant, we extend the method to include a frequency-based ICA stage that removes redundant time shift information. The digits speech recognition results show promising accuracy. Experiments show that the method based on ICA and Geometrical Learning outperforms HMM in a different number of training samples.

语前聋小儿人工耳蜗植入术后的言语康复

An Approach to the Rehabilitation of Prelingually Deaf Children After Cochlear Implantation Zheng Xiujin(Medical Psychology) Directed by Professor Yin WenGang Abstract Objective: To sum up the acquirement rule of speech and language capability which is for the prelingually deaf children after cochlear implantation by listening and language rehabilitation training and to investigate the factors that affect rehabilitation speed. Method: Sixty-four children received a cochlear implant at the age of 2 to 5 years from 2001 to 2005. They begin to be trained under group pattern after switch on 1 month. The whole training program lasted more than 7 months; after that, according to the teacher’s plan the training program was to be continued at home. Result: The period is 108±7.7 days that they can pronounce correctly 50 percent of all of simple-finals and compound-finals, the period is 115.0±7.8 days that they begin auditory repeating, the period is 135.3±10.9 days that they can speech the first specific word independently and the period is 200.3±13.9 days that they can speak 70 words and come into tri-gamut-word and two-word sentence period. The patient that is the group at the age of 2-3 years can take part in normal kindergarten after switch on about 10 months. There are no significant differences in various grades of speech-language development with different age groups and so do with different sex groups. There are significant differences in various grade of speech-language development with various IQ group (P<0.01) and so do with using and not using hearing aids before implantation. Conclusion: From the research we find that the speech and language development sequence is the same level between the prelingually deaf children of 2 to 5 years who received cochlear implant after speech training and normal children and which are stages of uncomplicated sound production, continuous syllabic (babbling), speech sprout, single-word utterances and two-word utterances in proper order. The time is short significantly and the reason is that cognition capability is enhanced along with the increase of age. The intelligence is main factor that affect rehabilitation speed and the speed in the group of high IQ is faster than common IQ. It is not because of the dominance cognition of the senior group that makes the increasing of the rehabilitation, it even makes slowly. The reason of which is that the senior group are exposed the language environment too late to achieve speech and language development. So we should perform an operation and training early. The effectiveness of rehabilitation after cochlear implantation is improved by using hearing aids before implantation. The reason is auditory stimulate can be benefit of to deaf children. The rehabilitation speeds in the children at the age of 2 to 5 years have nothing to do with sex. Key words: cochlear implant; speech therapy; paediatric rehabilitation