67 results about "Vowel" patented technology

The invention provides a vocal music training vowel pronunciation quality evaluation method based on auditory and visual spatial-temporal feature fusion, and the method comprises the steps: collecting vowel pronunciation audio signals and corresponding videos of a singer, and constructing a multi-modal data set; generating a fractional order Mel spectrogram for the audio signal through short-time fractional order Fourier transform of an adaptive order; extracting time sequence features and spatial features of the fractional order Mel spectrogram, and fusing the time sequence features and the spatial features through a gating mechanism to generate audio spatio-temporal features; face visual features in the video are extracted and fused with the audio spatio-temporal features through a cross attention mechanism, and the cross attention mechanism is integrated with a periodic modeling network; the fused features are input into a classifier, a dynamic weight multi-mode cosine loss function training model is adopted, the dynamic weight multi-mode cosine loss function dynamically adjusts the sample weight through a confusion matrix, and the weight is increased for the samples with classification errors based on the historical frequency mistaken division times of the samples; and outputting a pronunciation quality evaluation result.

The invention discloses a dysarthria speech evaluation system based on acoustic analysis. The dysarthria speech evaluation system comprises a speech evaluation module, a system management module and a cloud management platform, the speech evaluation module is used for performing vowel composition evaluation, voice evaluation, definition evaluation and composition motion evaluation on the user; the system management module is used for carrying out login authentication management, authority management, data management and evaluation record management on a user, and maintaining the safety of system operation and the integrity of data; and the cloud management platform is used for performing real-time data transmission and data analysis on the speech evaluation module and the system management module to complete dysarthria speech evaluation. According to the invention, objectivity and standard consistency of dysarthria assessment are improved.

The invention provides a human voice similarity detection method and system and a storage medium, and the method comprises the steps: obtaining a to-be-detected audio, and carrying out the preprocessing of the to-be-detected audio; performing feature extraction on the preprocessed to-be-detected audio to obtain audio features, and inputting the audio features into a pre-trained acoustic model for phoneme matching to obtain a vowel phoneme sequence; determining formant data of the audio to be detected according to the timestamp of each vowel phoneme in the vowel phoneme sequence, and determining a formant value of each vowel phoneme according to the formant data; and according to the formant value, calculating a formant difference value between the same vowel phonemes in the different to-be-detected audios, and according to the formant difference value, determining the human voice similarity between the different to-be-detected audios. According to the embodiment of the invention, the human voice similarity between different to-be-detected audios can be effectively determined based on the formant difference value, and the accuracy of human voice similarity detection is improved.

A voice disease recognition method based on MFCC and CNN comprises a patient audio acquisition module, an audio data preprocessing module, an MFCC feature extraction module, a classification model construction module and a patient voice disease category recognition module which are connected in sequence. The audio data preprocessing module uses a VAD endpoint detection algorithm to cut and unify recorded effective segments, and the MFCC feature extraction module performs operations such as weighting, windowing, transformation and filtering on the cut audio to obtain an exclusive MFCC feature map as a training object of a downstream classification task; the classification model construction module feeds a feature map containing pathological information to the voice disease recognition module. According to the method, the voice information of the vowel pronunciation of the Chinese pinyin of the patient is utilized to realize the classification and identification of four voice diseases (spasmodic dysphonia, vocal cord paralysis, vocal cord nodules and vocal cord polyps) with similar pathological expressions.

The invention relates to the technical field of audio signal processing. The invention provides a method, system and device for predicting pulmonary nodules through sound and a storage medium. The method comprises the following steps: in a quiet test environment, directionally collecting a sound signal of a patient through an audio sensor; wherein the sound signals comprise breath sounds, cough sounds, vowels and sentences; performing noise reduction processing on the collected sound signals to obtain a noise reduction data set; extracting multi-dimensional voiceprint features from the noise reduction data set, and constructing a sound feature matrix; and performing multi-modal fusion analysis on the sound feature matrix and clinical data of the patient, inputting the sound feature matrix and the clinical data into a sound prediction model optimized by a focus loss function, and outputting a pulmonary nodule risk prediction result and a visual diagnosis report. The problems that the misdiagnosis and missed diagnosis rate is high, the radiation risk is large and the equipment dependence is strong when the pulmonary nodules are examined by the existing iconography, and the characteristic analysis is single, the noise immunity is poor and the screening accuracy is insufficient in the sound detection technology are solved.

The invention discloses a mandarin training correction method for voice processing, and relates to the technical field of voice signal processing, and the method comprises the steps: recording the voice when a user reads a training text, and the amplitude-frequency feature sequence of each read character voice; constructing corresponding vowel feature vectors and initial feature vectors; detecting non-standard vowel syllables of the user; detecting non-standard initial syllables of the user; and prompting the user, and broadcasting the corresponding standard mandarin syllable pronunciation and spelling method to the user so as to train and correct the mandarin of the user. According to the method, the specific syllables of the user are accurately captured and carefully recognized, the pronunciation and spelling problems of the user are effectively pointed out, mandarin training and correction of the user are more efficient and accurate, and the method has great significance in improving the language ability and communication level of the public.

The present invention discloses a voice analysis method for key feature parameters of freezing gait symptoms in Parkinson's disease based on the AdaBoost algorithm. Step 1: Collect continuous and stable vowels of Parkinson's disease patients and record whether the Parkinson's disease patients have freezing gait symptoms; Step 2: Perform denoising preprocessing on the voice signals and remove the silent segments; Step 3: Extract various voice features; Step 4: Use the CART algorithm to perform feature selection on the original features and screen out the key features that can effectively represent the information of freezing gait symptoms; Step 5: Train the AdaBoost model; Step 6: Input the feature vector of the voice to be measured into the model to obtain the key feature parameters of the freezing gait symptoms in Parkinson's disease. The present invention uses the AdaBoost algorithm to analyze the freezing gait symptoms in Parkinson's disease, improves the model accuracy by using ensemble learning, and reduces the cost of early analysis of the freezing gait symptoms in Parkinson's disease.

The present invention relates to a system and method configured for analysing acoustic parameters of speech to detect, diagnose, predict and / or monitor progression of a condition, disorder, or disease, and more particularly, any of paediatric and adult neurological and central nervous system conditions including but not limited to low back pain, multiple sclerosis, stroke, seizures, Alzheimer's disease, Parkinson's disease, dementia, motor neuron disease, muscular atrophy, acquired brain injury, cancers involving neurological deficits, paediatric developmental conditions and rare genetic disorders such as spinal muscular atrophy. The system and method extracts a first formant data set from words spoken by an individual and uses these to classify the vowels in the words on a first computing device, such as a mobile smart phone equipped with a microphone into which an individual speaks. The system stores at least some of these frequencies for the vowel formants in a second formant data set as a recorded file and provides the second formant data set as input to acoustic metrics to generate score data from which an assessment is made to determine the articulation level of the vowels in the words spoken by the individual, allowing allow for detection, diagnosis, prediction and / or monitoring progression of the condition, disorder, or disease.

The invention discloses a multidirectional sliding Chinese character pinyin input method and a matrix type keyboard layout system, and belongs to the technical field of human-computer interaction of touch screen equipment (IPC classification number: G06F3 / 0488, G06F3 / 0323G06F 40 / 274). Aiming at the problems of complex vowel operation redundancy, initial and final combination conflict and the like in the existing sliding input method, the invention provides the following schemes: 1, the multidirectional sliding input method comprises the following steps of: starting sliding from any initial consonant or vowel (containing a zero initial consonant 0 / er key) on the basis of a matrix keyboard layout; different vowels or vowel combinations are mapped every time sliding is performed by one key in different directions or continuous sliding is performed. 2, multi-direction sliding input logic: defining an 8-direction sliding mapping er to be rightward-or-generated from e in a layout E; the method has the technical effects that the input efficiency is improved by more than 60% (high-frequency syllable steps are reduced by 70%), the false touch rate is lower than 5%, the national standard pinyin library is covered by 100%, and the method is obviously superior to a traditional touch screen input scheme.

The embodiments of the present application provide a method, device, electronic device and computer-readable storage medium for oral evaluation, which relate to the field of speech recognition. The method comprises: obtaining spoken audio, marking at least one vowel segment of the spoken audio; obtaining the rhythm feature of the spoken audio according to the duration of at least one vowel segment; and evaluating the rhythm of the spoken audio according to the rhythm feature. When the embodiments of the present application are applied in cloud education, especially oral rhythm education, the rhythm level of the user's spoken language can be judged more accurately.

The utility model discloses an alphabetical keyboard for Chinese teaching, which comprises a keyboard main body, a pressing plate and a chip, the side wall of the keyboard main body is provided with alphabetical key positions, the alphabetical key positions are provided with single vowel key boards, the top of each single vowel key board is provided with an X-shaped groove, the X-shaped groove is internally provided with a movable groove, and the movable groove is provided with a through hole. A movable groove is formed in the top of the pressing plate, a tone electric contact is arranged in the movable groove, a movable column is arranged in the X-shaped groove, a first reset spring is arranged on the inner wall of the X-shaped groove, a column body extending into the X-shaped groove is arranged at the bottom of the pressing plate, a universal head is arranged at the bottom of the column body, and a light-sound electric contact is arranged at the top of the chip. The chip is electrically connected with the tone electric contacts through signal lines respectively, a second reset spring is arranged at the top of the chip, and the top of the second reset spring is fixedly connected with the base of the universal joint. According to the utility model, the tone of pinyin of a Chinese character can be directly observed, and the corresponding tone of the Chinese character can be learned.

A method of providing an instructional scaffold to person learning to read English language comprises displaying printed matter to the learner in the form of lists. Preferably text stories. The normal spacing of the letters in words is kept intact; in a first part of the method the rime portions of monosyllable words are bolded and made larger than the onset portions; and in a second part of the method, which also may be used independently, the sequential syllables of multisyllable words are emphasized by alternating plain font with bolded font and the long vowels are identified, for example by underscore, again with the words of any text being kept intact.

To provide a sound signal processing method capable of efficiently emphasizing voice of a user even in environment with much background noise.SOLUTION: A sound signal processing method includes: a step of receiving a sound signal; a step of determining vowels based on a spectral shape pf the sound signal within a prescribed first time period or determining voice based on a change rate of pitches of the sound signal within a prescribed second time period; and a step of adjusting a time characteristic or a frequency characteristic of the sound signal based on a result of vowel determination or voice determination.SELECTED DRAWING: Figure 3

A data structure and associated methods for analysis of a continuous 1,197,000-letter unvocalized Hebrew string referred to as the Word of God (WOG). The data structure contains only the twenty-two classical Hebrew letters and their five final forms, with no spacing, punctuation, vowelization, or editorial symbols. Intrinsic placement of the final letters enables deterministic segmentation of the string into 305,490 lexical units and 23,206 verses without external conventions. Fixed letter-number assignments provide a numeric architecture for evaluating substrings, detecting alterations, identifying encoded mathematical correspondences, and performing pattern analysis. The system preserves full semantic range by supporting multiple morphologically valid interpretations of unvocalized Hebrew strings. Methods for segmentation, numeric evaluation, reconstruction, integrity verification, semantic analysis, and mathematical pattern detection are provided thereby providing a reproducible foundation for computational and linguistic research.

: A method for enabling comprehension of speech by tactile stimulation is provided. The method includes steps as follows: receiving an audio input; performing an analog-to-digital conversion on the audio input; performing a DFT to convert the audio input to a frequency domain; extracting key features of the audio input based on a band of the audio input, wherein the key features contain frequencies that are representative of at least one vowel; and converting frequencies of the extracted key features to a range of tactile frequencies, which comprises performing a mapping process on the frequencies to shift or map them into a subset, such that the mapping process transfers the frequencies from a high-frequency interval to a low-frequency interval, wherein the low-frequency interval is a perceivable range of tactile frequencies.

To improve efficiency of registering words to a pronunciation dictionary of a voice recognition engine used for maneuvering a moving object.SOLUTION: A word registration method for registering words in a pronunciation dictionary of a voice recognition engine used to input dialogues uttered during maneuvering of a moving object, comprises: a step of extracting words included in the dialogues uttered during the maneuvering; a first gathering step of gathering one of the words with the same vowel arrangement pattern into one word by combining it with preceding and following words in the dialogues, when multiple words with the same vowel arrangement pattern among the extracted words exist; and a step of registering the extracted words and the words gathered into the one word to the pronunciation dictionary.SELECTED DRAWING: Figure 1

The invention provides a type II diabetes intelligent detection method based on an improved logistic regression integrated model, and belongs to diabetes intelligent detection, and the method comprises the steps: designing a voice vowel data collection scheme of a diabetic patient and a normal person, and constructing a data set: extracting voice audio features in the data set through the Praat voice analysis, and carrying out the standardization processing; feature selection is carried out based on Lasso regression and recursive feature elimination, and a training set, a verification set and a test set are divided; constructing a tree-shaped logistic regression model based on the attention mechanism, performing training by using the training set, performing verification by using the verification set, and dynamically determining an optimal prediction threshold value to obtain a trained tree-shaped logistic regression model based on the attention mechanism; and taking the test set as input, testing the trained tree logic regression model based on the attention mechanism, and obtaining a detection result. According to the method, the detection accuracy is improved under the condition of not depending on demographic characteristics.

The application discloses an input method, device and system based on number sequence and number sequence vowel definition and symbol mapping, which comprises the following steps: defining a number sequence and a number sequence vowel set, wherein the number sequence is a fixed sequence of numbers 1-9, 0 and an extended character, the number sequence vowel set comprises 11 groups of vowels arranged according to the number sequence, and each group of vowels corresponds to a unique number sequence coding bit; establishing a mapping relationship between the 11 groups of vowels and a number sequence input unit, wherein the number sequence input unit comprises at least 10 digital key positions and an extended character key position arranged according to the number sequence; and generating a candidate word list according to the defined number sequence and number sequence vowel set and the mapping relationship in response to a user input operation. The application solves the problem of inconsistent coding logic and multiple keystrokes of vowels in the prior art, significantly improves the input efficiency of Chinese pinyin, supports multiple input modes to share a unified coding system and reduces the learning cost of users.

The invention discloses an optimized arrangement scheme of a pinyin keyboard. The method is mainly based on a standard QWERTY keyboard layout, single vowel character keys, single vowels A, O, E, I and U and corresponding 24 tone character keys including grand, Yang, upper sound and lower sound which are unique to Chinese phonetic alphabets are expanded, optimization design is carried out on the layout of newly-added keys, a user can input the Chinese phonetic alphabets conveniently, rapidly and more completely, and the user experience is improved. And in cooperation with related computing equipment software, quick Chinese character input conforming to the natural language expression habit of Chinese can be carried out, and learning and popularization of Chinese and Chinese pinyin are facilitated.

To provide English teaching materials helping students intuitively acquire English pronunciation.SOLUTION: There is provided an English teaching material comprising a position identification member and a plurality of vowel cards. The position identification member includes a bimaxillary display for roughly representing a lateral cross-section of both jaws of a person, and a plurality of identifiers for respectively identifying a plurality of positions of a tip of the tongue during pronunciation. The plurality of vowel cards are each assigned to a different English vowel. The plurality of vowel cards have, on each one side, a face symbol imitating a human face and one or two of a plurality of identification displays. The face display includes a mouth shape diagram for graphically representing the mouth shape when pronouncing the corresponding vowel. The plurality of identification displays respectively have the same form as any of the plurality of identifiers.SELECTED DRAWING: Figure 1

The invention discloses a signal processing detection method based on an attention guidance learnable time domain filter bank. Comprising the following steps: S1, establishing a joint learning framework of a learnable time domain filter bank with attention guidance; s2, spectral features related to tasks are generated through the learning module, and acoustic features with biological significance are generated by using a learnable time domain filter; s3, guiding the learnable time domain filter to reserve useful frequency sub-bands through the multi-scale spectrum attention module; and S4, establishing a classification module, and generating the output of the segment-level label by taking the learned spectral features as the input through the classification module. The Mel spectral features in the existing deep SDD framework can be easily replaced by the arranged learning module, and the central frequency of the time domain filter concentrated in the specific formant range of Chinese vowels, especially in the frequency range of 600-700Hz can be learned, so that the time domain filter is a biomarker which is beneficial to distinguishing depression patients.

This product is a notebook paper with five lines representing vowels next to the writing space, with the vowels A, I, U, E, O marked at the beginning of each line, visualizing the finger movements for vowels when reading by hand. It can be used vertically or horizontally depending on the purpose. After writing the letters, mark the vowel positions on the five lines, connect the marks with lines, and visualize the vowels.

Provided are a method, apparatus, and medium for recognizing tones of speech. The method comprises: detecting the duration position of a vowel of a vowel in a speech to be recognized; detecting a tone core portion of the speech to be recognized based on the duration position of the vowel of the vowel; and identifying the tone category of the speech to be recognized based on the tone core portion. Thus, according to at least one embodiment of the present disclosure, the tone core portion can be more accurately detected within the duration position of the vowel of the vowel, thereby more accurately identifying the tone category.

The invention provides an information input device and a pinyin input method thereof. In a pinyin input mode, selective input of information is realized through an operation signal of a physical key, and the information input device comprises an initial input unit which is configured to switch initial pages in response to an operation signal of a first key and determine initial in the initial pages in response to an operation signal of a first rocker; the vowel input unit is configured to switch vowel pages in response to the operation signal of the second key and determine vowels in the vowel pages in response to the operation signal of the second rocker; and the Chinese character input unit is configured to respond to a pinyin confirmation signal of the third key, generate candidate Chinese characters according to the determined initial consonants and finals, and input selected Chinese characters according to operation signals of the cross key and the fourth key. The invention provides a technical scheme which accords with the operation characteristics of a general handle and can remarkably improve the pinyin input efficiency.

A computer-implemented method can include determining a speech transition within a speech signal, the speech transition including a change of sound; determining a mouth state based on the speech transition; determining a vowel transition during a vowel sound within the speech signal; and modifying a facial feature of an avatar based on the mouth state and the vowel transition.

The invention discloses a Korean Chinese character input system and a marking method thereof, and relates to the technical field of Chinese character input systems. The problem that an existing Chinese character Korean pronunciation input system cannot achieve the effect that one Chinese character corresponds to one Korean pronunciation character is solved. The Korean syllable consonant module comprises a tone module, a Korean syllable consonant module and a Korean syllable consonant module, the Korean syllable consonant module comprises a single syllable consonant unit and a compound syllable consonant unit, the Korean syllable consonant module comprises a single syllable consonant unit, a compound syllable consonant unit and a tail syllable consonant unit, and the Korean syllable consonant module and the Korean syllable consonant module comprise a left-right structure and an up-down structure. According to the method, pronunciation and tones of Chinese characters are accurately marked through continuous use and recombination of existing Korean letters, the Chinese characters can be directly learned and input through pronunciation of the Korean letters, and the Chinese characters can be accurately spelling and read according to Korean sound marks; corresponding Chinese characters can be input and typed according to the pronunciation of the Chinese characters and the Korean pronunciation spelling method, so that the Chinese learning efficiency is improved.

The invention provides a vowel recovery method and device, electronic equipment and a storage medium, and belongs to the technical field of natural language processing, the vowel recovery method comprises the steps that a first to-be-processed text is acquired, and the first to-be-processed text comprises a first text needing vowel recovery; the first to-be-processed text is input into the vowel recovery model for variable note label synchronous prediction, prediction labels output by the vowel recovery model are obtained, and the prediction labels are three types of variable note labels corresponding to each character in the first text; and determining a target text after vowel recovery based on the first to-be-processed text and a prediction label output by the vowel recovery model. In the process, the three types of variable note tags corresponding to each character in the first text can be synchronously predicted, and conflicts among different variable note tags are avoided, so that the variable note tag is accurately predicted for each character in the first to-be-processed text, and the accuracy of vowel recovery is improved.

The present application proposes a vocal singing practice quality grade evaluation method of fractional order spectrogram deep learning, including the following steps; Step S1, collect the audio signal of the singer's vocal vowel singing practice, and according to the singing index, label the corresponding quality grade, construct the sample data set, and use it for model training, testing and verification; Step S2, convert the audio signal into a series of fractional order spectrograms; Step S3, construct the fractional order spectrogram deep feature extraction network based on DenseNet and channel attention mechanism in the model, input the extracted fractional order spectrogram deep features into the BiLSTM network, and extract the time sequence features of the singing practice signal; Step S4, the quantum fireworks algorithm is used to optimize the hyperparameters of the kernel extreme learning machine of the model, and the extracted time sequence features are mapped to a high-dimensional space for quality grade decision, forming the evaluation result; Step S5, train the model; The present application can better adapt to the characteristics of non-stationary signals and provide more accurate spectrum analysis.

The invention discloses an English syllable u feature wavelet coefficient extraction method based on a spline interpolation wavelet neural network, and the method comprises the steps: firstly carrying out the normalization and threshold preprocessing of an audio signal, and effectively removing the interference of environment noise; secondly, constructing a three-layer neural network feedback matrix based on a six-order spline wavelet function, and generating a feedback matrix through transposition operation and inverse matrix calculation of a global matrix psi; then, inverse discrete Fourier transform is utilized to construct a criterion function containing frequency domain errors; and finally, dynamically adjusting the weight of an output layer through iterative training, and terminating training when the modulus value of the criterion function is smaller than a training error iteration ending condition, so as to obtain a wavelet coefficient set representing the characteristics of the longhairy sound u. According to the method, the frequency domain localization characteristic of the six-order spline wavelet is innovatively combined with the adaptive learning of the neural network, the anti-noise performance is improved while the feature extraction precision is ensured, and the problem of individual pronunciation difference is solved.

The edge device-oriented lightweight voice band expansion method, device, terminal and medium provided by the application belong to the technical field of voice signal processing, and the method comprises the following steps: obtaining a logarithmic domain narrowband audio signal amplitude spectrum and a logarithmic domain mixed amplitude spectrum; constructing a white noise amplitude spectrum; inputting the logarithmic domain narrowband audio signal amplitude spectrum, the logarithmic domain mixed amplitude spectrum and the white noise amplitude spectrum into a trained voice bandwidth expansion model to generate a first high-frequency component corresponding to a consonant in the narrowband audio signal and a second high-frequency component corresponding to a vowel in the narrowband audio signal, and then obtaining a predicted amplitude spectrum; expanding phase information of the narrowband audio signal, generating a wideband audio signal according to the predicted amplitude spectrum and the expanded phase information of the narrowband audio signal, and outputting the wideband audio signal. The voice bandwidth expansion model is used to reconstruct the consonant, so that the reconstructed consonant component has higher fidelity, and the intelligibility of the reconstructed voice is ensured.