47 results about "Dysarthria" patented technology

The invention provides a system for evaluating hearing-speech rehabilitation training and curative effect of patients with post-stroke dysarthria and a device thereof. The system comprises a patient selecting module (1), an effect evaluating module (2), a training module (3) and a clinical curative effect evaluating module (4). The invention also provides a method for evaluating hearing-speech rehabilitation training and curative effect of patients with post-stroke dysarthria. The method comprises the following steps: selecting patients with post-stroke dysarthria, evaluating before training, training language, evaluating after training and evaluating clinical curative effect. The system and the method are used for training pronunciation and reading in hearing-speech rehabilitation treatment of the patients with post-stroke dysarthria, providing curative effect evaluation, improving pronunciation accuracy degree and continuous pronunciation coordination ability of the patients, subdividing treatment grades according to different conditions of the patients, making individual training schemes and improving pertinence, relieving working strength of hearing-speech rehabilitation therapists and effectively improving the working efficiency and the individual treatment training effect.

The invention discloses an adult hearing and speaking rehabilitation system comprising an information management module, a parameter setting module, a single character pronouncing assessment module, a single character pronouncement training module, a word reading training module, a speech recording and playing module, an automatic speaking assessment module and a random sequence producing module. The system is applied to speaking and reading training for aphasia patients with repetition impediment or loud reading impediment and dysarthria during speaking rehabilitation, the speaking feedback ability of the aphasia patient is improved, the pronouncing accuracy level of the dysarthria patient is raised, the continuous pronouncing coordinate ability is improved, and the work intensity is reduce significantly for speaking therapists. Multisensory reinforcing stimulation is performed on the patient in multimedia interacting manners of graphs, texts, dynamic images and voices, the subjective initiation of the patient for the rehabilitation training is improved, and the rehabilitation training effect is improved; the simple, boring and repeated work can be reduced for the therapists.

The invention discloses a system for multi-dimensional measurement of dysarthria based on a real-time articulation modeling technology. The system comprises a voice input unit, a discriminating unit, an analytical unit, a partition unit and a marking unit. The voice input unit is used for inputting voice data needing an analysis, the discriminating unit judges the voiceless and voiced types of the voice data, the analysis unit extracts and analyzes acoustic parameters of the voice data according to the voiceless and voiced types, the partition unit partitions the voice data according to the acoustic parameters to generate voice sections, the marking unit marks the partitioned voice sections according to the acoustic parameters and obtains measurement results. The smallest voice units which form single-syllable words, disyllabic words or polysyllabic word are separated, through confluence analysis of articulation multi-dimensional parameters, measurement is carried out on Chinese voices, and self feedback of dysarthria rehabilitation training is achieved. A method level and a modern technology level are combined to form the real-time articulation modeling technology, and a method for the multi-dimensional measurement of the dysarthria based on the real-time articulation modeling technology is further disclosed.

The invention provides a dysarthria identifying method. The dysarthria identifying method includes the steps that sample data are acquired, calibrated and denoised, wherein the sample data comprise the voice data and the organ motion data; the resonance peak value of the voice data is extracted, and sample acoustic parameters are calculated; the tongue and lip deviation displacement of the organ motion data is calculated; sample kinematics parameters of the organ motion data are calculated; correlation calculation is carried out on the resonance peak value and the tongue and lip deviation displacement, and multiple regression calculation is carried out on the sample acoustic parameters and the sample kinematics parameters to obtain a regression equation; collected data are acquired, and target kinematics parameters are calculated according to the regression equation; the collected data are identified and classified according to the sample kinematics parameters and the target kinematics parameters. Dysarthria identifying accuracy can be effectively improved by the adoption of the method. The invention further provides a dysarthria identifying device and system.

The invention discloses a cerebral stroke dysarthria risk prediction method based on ResNet and a LSTM network. The method comprises the following steps: firstly, collecting voice information througha recording device, then preprocessing the voice information, and extracting voice feature parameters MFCC (Mel-scale Frequency Cepstral Coefficients); then constructing a ResNet and LSTM neural network model to train the MFCC feature parameters, and extracting depth feature information of a speech signal; and finally inputting the MFCC feature parameters to be tested into a trained model, and predicting the risk of the cerebral stroke dysarthria. The method has the advantages of being convenient, quick, cost-saving, high in prediction accuracy and the like.

The invention discloses a method for estimating severity of dysarthria based on deep audio features. The method comprises steps that acoustic features are extracted; the acoustic features are inputtedto the deep neural network with a bottleneck layer, and depth audio features are extracted from the bottleneck layer; the depth audio features are taken as input, and the Baum-Welch algorithm is utilized to train hidden Markov models; and lastly, the depth audio features of test voice samples are sequentially inputted into the four trained hidden Markov models, four output probabilities are obtained through utilizing the Viterbi algorithm, and the category corresponding to the model with the highest output probability is the dysarthria severity, namely, the decision result. The method is advantaged in that the depth audio features are deep transformation features, compared with traditional acoustic features, feature difference of the dysarthria voice can be more effectively described, andthe more excellent effect in estimating the dysarthria severity can be obtained.

The invention discloses a multi-dimensional dysarthria measuring system based on real-time vocal tract shape correction. The multi-dimensional dysarthria measuring system comprises a voice input unit, an analysis unit, a marking unit, a parameter setting unit and a model generating unit, wherein the voice input unit is used for inputting voice files to analyzed; the analysis unit comprises an unvoiced and voiced sound type distinguishing module for distinguishing unvoiced and voiced sound types, a formant extraction module for extracting formants and a spectrogram analysis module for spectrogram calculation; the marking unit is sued for marking key frames of the formants according to the formants and spectrograms; the parameter setting module is used for setting and adjusting vocal tract shape parameters; the model generating unit is used for drawing the key frames into a vocal tract shape model according to the vocal tract shape parameters. The system displays movement conditions of articulators intuitively and monitors related parameters of the articulators to achieve articulation self feedback of dysarthria recovery trainings. According to the system, the method level and the modern technical level are combined to form a real-time vocal tract shape correction technology. The invention further discloses a multi-dimensional dysarthria measuring method based on the real-time vocal tract shape correction.

The invention discloses a dysarthria vowel evaluation template and method. The template comprises a normal vowel elliptical distribution template and an evaluation report base plate, the upper surfaceof the normal vowel elliptical distribution template is a transparent plate, the transparent plate comprises a vertical and horizontal coordinate axis with a numerical scale and the elliptical distribution range of multiple monophonic resonance peak spatial distribution; the evaluation report base plate also comprises a vertical and horizontal coordinate axis with a numerical scale, same as the transparent plate, an internal groove is formed in the edge of lower portion of the transparent plate, the evaluation report base plate can be inserted into the groove, and after the evaluation reportbase plate is inserted into the groove, the coordinate axis of the transparent coincides with that of the evaluation report base plate. The objective evaluation method can be provided, the working pressure of a therapist can be relieved through artificial intelligent means, and then a therapist conducts more precise and efficient speech rehabilitation training on the patients suffering from dysarthria.

The invention relates to a breathing training device for dysarthria rehabilitation. The breathing training device comprises an air blowing pipe, a conversion pipe, a three-way pipe, a first pipe body, a second pipe body and a buoy tube, wherein the first pipe body is connected with a training device in a first mode, the second pipe body is connected with a training device in a second mode, and two different training modes can be switched through the rotation of the switching tube in the three-way pipe. The breathing training device for dysarthria rehabilitation has two training modes, the training mode conversion can be realized according to patients with different requirements in different age groups, the structure is simple and reasonable, the conversion is convenient, during the breathing training, the force of the breathing muscle at the throat part and the like can be effectively increased, in addition, the staying time of the airflow at the throat part is longer, so that a repeated massage and impact effect is realized on the muscle of the throat part, therefore the feeling function rehabilitation of the sound producing muscle of the throat part can be favorably enhanced, and great help is realized on the speech function rehabilitation.

A breathing articulation training apparatus and a training method thereof are disclosed. A patient selection module is used to select a patient who is suitable for the breathing articulation training, a curative effect evaluating module is used to evaluate pronunciation of the patient before training, a breathing sounding training module is used to perform 'character tips' breathing sounding training for the patient, and a basic articulation training module is used to perform basic articulation training for the patient. After the breathing sounding training and the basic articulation training, the curative effect evaluating module is used to evaluate the curative effect after training and determine the difference before and after training and the training effect according to the pronunciation evaluation before training and the curative effect evaluation after training. The breathing articulation training apparatus combines the character tips with the basic articulation training to solve the difficult problem of dyspnea in speech training. The breathing control ability of a patient during speaking is effectively improved, and the articulation ability can be improved comprehensively. An effective, simple and inexpensive verbal rehabilitation method can be provided for patients with dysarthria and breathing control abnormality.

A system for improving dysarthria speech intelligibility and method thereof, are provided. In the system, user only needs to provides a set of paired corpus including a reference corpus and a patient corpus, and a speech disordering module can automatically generate a new corpus completely synchronous with the reference corpus, and the new corpus can be used as a training corpus for training a dysarthria voice conversion model. The present invention does not need to use a conventional corpus alignment technology or a manual manner to perform pre-processing on the training corpus, so that manpower cost and time cost can be reduced, and synchronization of the training corpus can be ensured, thereby improving both training and conversion qualities of the voice conversion model.

The invention belongs to the information processing technology field and especially relates to the statistical classification method of dysarthria pronunciation movement abnormal distribution. An articulator pronunciation movement statistics problem is solved. The method comprises the following steps of S100, drawing the distribution maps of a tongue tip, the center portion of a tongue and the root of the tongue in the pronunciation movement intervals of front and back, left and right, and up and down directions; S200, taking 25 mm as a threshold value and calculating the proportion of the pronunciation movement interval which is greater than the value; S300, fitting pronunciation movement interval distribution through lognormal distribution; and S400, fitting through normal distribution,using the 2.58 standard deviations of the normal distribution as the threshold value, and calculating the proportions of the abnormal pronunciation data of patients with dysarthria and normal people.In the invention, from the front and back, left and right, and up and down directions of tongue portion space movement, the pronunciation movement interval distribution of a speaker in three directions is researched, and then the patients with dysarthria and the normal people are counted according to the proportion of the abnormal pronunciation movement interval.

The invention provides an automatic dysarthria evaluation system and method based on speech recognition. The system comprises a first feature extraction unit, a second feature extraction unit, a feature splicing unit, a multi-layer perceptron and an evaluation unit. The feature splicing unit is in communication connection with the first feature extraction unit, the second feature extraction unit and the multi-layer perceptron, and the evaluation unit is in communication connection with the multi-layer perceptron. The first feature extraction unit is used for extracting traditional sentence-level acoustic features. The second feature extraction unit extracts frame-level audio annotations and the frame phoneme-probability relationship. The feature splicing unit is used for splicing the features extracted by the first feature extraction unit and the features extracted by the second feature extraction unit. The multi-layer perceptron outputs the individual sentence obstacle degree and the corresponding prediction probability based on the spliced features. The evaluation unit obtains an overall evaluation result by using the prediction probability information of the individual sentences. According to the invention, the accuracy and stability of dysarthria estimation can be improved.

The invention relates to a double-mode breathing training machine used for dysarthria recovery. The double-mode breathing training machine comprises a bubble tube, a conversion tube, a three-way tube, a tube body I, a tube body II and a buoy tube. The tube body I is connected with the training machine in a mode I, and the tube body II is connected with the training machine in a mode II. The two different training modes can be switched through rotation of the conversion tube in the three-way tube. The two training modes are adopted for the double-mode breathing training machine used for the dysarthria recovery and can be switched according to different age groups and patients with different requirements. The double-mode breathing training machine is simple and reasonable in structure and convenient to convert, when the breathing training is performed, strength of the breathing muscles including the laryngeal part of pharynx and the like can be effectively increased, besides, airflow has massaging and impacting effects on the muscles of the laryngeal part of pharynx because the airflow retention time is long in the laryngeal part of pharynx, recovery of a feeling function of the articulation muscles of the laryngeal part of pharynx is facilitated, and the double-mode breathing training machine is more helpful to verbal function recovery.

According to the fMRI data processing method for functional connection of the language functional area of facial nerve paralysis, image data with high spatial resolution can be obtained while no injury is caused to a human body, and therefore the language functional area corresponding to facial nerve paralysis accompanied by dysmnesia can be accurately positioned. The method comprises the following steps: acquiring fMRI data of a plurality of adult peripheral facial paralysis patients and a plurality of health control persons by using a magnetic resonance imager and a standard head orthogonalcoil; adopting DPARSF software to preprocess the data, and removing abnormal data and noise; selecting 16 ROIs (Regions of Interest) of a base section area and a language functional area for functional connection FC analysis; comparing FC differences between the patient group and the control group by adopting a double-sample t test, carrying out multiple comparison and correction by adopting an FDR (False Discovery Rate) method, and setting a threshold value P to be less than 0.05; and evaluating the facial nerve function of all subjects by adopting a dolomb polyhedral nerve grading method TFGS, and analyzing and evaluating the correlation between the abnormal FC of the patient suffering from facial nerve paralysis and the oral muscle movement TFGS score.

A self-induced dysarthria game that forces communication of specially-chosen phrases or performance of other common or humorous tasks involving use of the cheeks or lips despite an induced speech impairment, so that players inevitably experience initial failure but must compensate to win. Game play may involve individual competition or team play. A mobile software application for enabling game play is also disclosed.

The invention discloses a method for evaluating dysarthria in children by optimizing and selecting acoustic parameters based on a data mining technology. Objective acoustic features of a tested childare collected, extracted and analyzed; a LASSO regression function is adopted; a generalized linear model is fitted; variable selection is carried out; an integrated weight dependent variable is extracted; therefore, acoustic feature parameters having important reference significance on dysarthria in Putonghua-speaking children and the weights of all kinds of acoustic feature parameters are selected; and thus, the foundation can be laid for objective evaluation of dysarthria in children. A LASSO method is adopted for the first time in the invention; the correlation of 40 acoustic feature parameters and all kinds of dysarthria in children is analyzed; the weight acoustic features of all kinds of dysarthria in children are found; and the most contributive acoustic parameters for evaluating the dysarthria in Putonghua-speaking children are explored.

The invention discloses an acoustic index-based dysarthria grading evaluation method. The method comprises the following steps: acquiring voice data of a patient with dysarthria after cerebral apoplexy; extracting objective acoustic feature intelligibility of the voice data, and collecting, extracting and analyzing acoustic indexes of the subject, the objective acoustic feature intelligibility being a pathological voice analysis index which is high in recognition degree and good in sensitivity at home and abroad; determining critical values of slight abnormality, moderate abnormality and severe abnormality of the voice by using the obtained acoustic feature intelligibility based on an automatic clustering algorithm K-means of artificial intelligence; using the intelligibility critical value for clinically evaluating the severity level of the dysarthria of the subject. According to the method, evaluation errors caused by subjective factors such as the technical level of technicians, subjective judgment and regional difference are reduced; meanwhile, operation is easy, and consumed time is short.

The invention relates to a rapid dysarthria detection method based on modal decomposition. The method comprises the following steps: collecting an original voice signal; preprocessing the original voice signal; performing acoustic feature extraction on the framed and windowed signal S based on modal decomposition to obtain statistical features; the statistical features are input into a machine learning classifier, dysarthria detection is achieved, and the machine learning classifier is a support vector machine (SVM) model. According to the method, the limitation of traditional acoustic features in a nonlinear time-varying system is overcome, the IMF obtained through decomposition contains time-frequency information of original audio signals on different levels, voice physiological information of dysarthria patients can be well captured, pathological changes of vocal organs are reflected, and the accuracy of the voice physiological information is improved. The accuracy and robustness of dysarthria detection are improved; the method can adapt to non-linear and non-stable voice signals, and further improves the detection effect of dysarthria.

The invention discloses a drug composition for treating cerebral thrombosis; the active components of the drug composition mainly comprise, by mass, 0.10-0.20 part of picrocrocin, 1.6-2.0 parts of midecamycin acetate, 0.35-0.42 parts of North America eriodictyol; the adult drug dosage is 240-260 mg active component/kg/day. The drug composition has the effects of clearing heat and promoting diuresis, invigorating the circulation of blood and detoxifying, and dispelling wind and removing obstruction in the meridians; the composition is featured by quick treatment effect and no relapse after curing specific to dizziness, nausea, sickness, diplopia, crossed akinesia and sensory disturbance, dysarthria, dysphagia, drinking choke and other symptoms caused by treating cerebral thrombosis; after long-term taking, the composition is free from obvious damage to liver and kidney, and worthy of extensive popularization and application clinically.

A device and a method for clarifying dysarthria voices is disclosed. Firstly, a dysarthria voice signal is received and framed to generate dysarthria frames. Then, the dysarthria frames are received to retrieve dysarthria features. Finally, the dysarthria features are received. Without receiving phases corresponding to the dysarthria features, the dysarthria features are converted into an intelligent voice signal based on an intelligent voice conversion model. The intelligent voice conversion model is not trained by the dynamic time warping (DTW). The present invention avoids the phase distortion of the voice signal and provides more natural and clarified voices with low noise.