57 results about "Consonant" patented technology

The invention provides a Suzhou dialect medical voice electronic medical record conversion system and method, and the system comprises an acoustic feature extraction module which is used for extracting the acoustic features of an input voice signal; the dialect tone recognition module is used for recognizing a multi-tone system of Suzhou dialects; the voiced sound processing module is used for detecting voiced sound initial consonants in Suzhou dialects and performing acoustic feature mapping; the medical term mapping module comprises a corresponding relation library of dialect medical vocabularies and standard medical terms and a context-based ambiguity resolution unit; the speech recognition engine comprises an acoustic model, a pronunciation dictionary and a language model; and the medical record generation module is used for converting the identification result into a structured electronic medical record. According to the method, a sliding window processing strategy is adopted, continuous voice input of a doctor can be effectively processed, a long-time voice input scene is supported, and various requirements in actual clinical application are met.

The invention relates to the technical field of Russian pronunciation teaching, and discloses a Russian pronunciation error correction system based on AI speech recognition, and the system comprises a speech input module which is used for collecting a Russian speech signal of a user; the rule engine module is internally provided with a Russian linguistics rule library, comprises an accent shift rule library and a vowel weakening acoustic threshold library, and is used for detecting pronunciation errors based on rules; the deep learning evaluation module comprises a neural network model subjected to adversarial data enhancement training, and is used for extracting phoneme-level and rhythm-level features from the voice of the user and detecting errors; a confrontation data generation module; a display module; and an AI interactive teaching module. According to the method, Russian speech data with preset phonemes and rhythm errors are synthesized through the generative adversarial network, the generator directionally injects error features through time-frequency convolution, the discriminator and the evaluation model share a feature extraction layer, and the detection sensitivity of the model to complex pronunciation errors such as native language migration consonant confusion is improved.

The present invention discloses a method for designing an interference noise of speech based on the human speech structure, including the following steps: (1): obtaining a large amount of speech data containing different speakers and different speech contents, extracting voiceprint information, and then building an initial speech data set; (2): for each user, obtaining a small amount of speech data of the user, extracting voiceprint information, and then matching the most similar speech data in the initial speech data set; (3): performing data augmentation on the matched speech data; (4): segmenting the augmented speech data with a phoneme segmentation algorithm to form a vowel data set and a consonant data set; (5): constructing three noise sequences based on the vowel data set and the consonant data set, and performing superimposition to obtain an interference noise; and (6): continuously generating and playing randomly generated interference noise, and continuously injecting the interference noise into recordings to implement continuous interference. With the present invention, the interference noise cannot be removed from the speech, thereby avoiding the leakage of user privacy information.

The keyboard according to the present invention is characterized in that a user who is used to input Japanese by using Roman can easily grasp the keyboard without having a large sense of fall, and the number of keystrokes required is greatly reduced compared to Roman input, thereby enabling more efficient input. According to the Japanese keyboard provided by the invention, not only consonants of i sections or a section a, but also large letters (,) of kana (,,), '-', 'hook, large letters (,) of kinphonic sound, small letters (,) of kinphonic sound, continuous characters (-) and full stop '.' in the Japanese keyboard are provided. The Japanese keyboard has the advantages that the consonants are not only consonants of i sections or'a) sections, but also consonants of kana (,,), '-', 'hook', large letters (,) of kinphonic sound, small letters (,) of kinphonic sound; therefore, the number of keystrokes for inputting Japanese can be significantly reduced.

In a sound processing method, event information relating to an event is acquired from an information source device or an information source service (S1); a step (S4) of determining a character string to cause the speech device to sound on the basis of the acquired event information; dividing the determined character string into one or more sub-character strings (S5); generating a sound signal according to the character string (S7); a correction step (S6, S8) for correcting the generated sound signal by performing a filtering process in which a first filter corresponding to the characteristics of the consonants is applied for each sub-string; and outputting the corrected sound signal (S11).

A voice intelligibility enhancement system is disclosed comprising at least one in-ear headphone device arranged with an ear canal facing portion and an environment facing portion. The device includes an acoustic path including a vent, the acoustic path coupling an environment-facing portion with an ear canal-facing portion, and an electro-acoustic path including a microphone at the environment-facing portion, a filter, and a speaker at the ear canal-facing portion. The acoustic path is arranged to transmit acoustic sound in a vowel-dominant frequency range, and the electro-acoustic path is arranged to acoustically reproduce a sound signal in a consonant-dominant frequency range and in the vowel-dominant frequency range, and the electro-acoustic path is arranged such that contributions from the acoustic path within the vowel dominant frequency range are compensated by the electro-acoustic path to improve the signal masking ratio. A method for enhancing speech intelligibility is also disclosed.

The invention discloses a semantic analysis method for voice in a crowded environment. The method comprises the following steps: acquiring voice signal data and lip movement video stream data of a target user; extracting a lip motion feature sequence, and mapping the lip motion feature sequence into a predicted speech feature vector; inputting a voiceprint separation model, separating a voice segment of a target user from the mixed voice signal, and generating pure voice data features; performing time domain segmentation on the pure voice data features to obtain a voice signal time domain waveform of a single character; matching the single character voice signal time domain waveform with an initial consonant and vowel time domain waveform library to obtain pinyin expression corresponding to each character; and carrying out tone combination correlation analysis on the pinyin expressions of the continuous single characters to obtain the meaning of the voice segment of the target user. The method has the advantages that the voice of the target user is effectively extracted by combining the lip movement video stream and the voice signal data and utilizing the deep learning and voiceprint separation technology, and the voice recognition accuracy in the noisy environment is remarkably improved.

The present disclosure provides a non-transitory computer readable medium having instructions stored thereon that, when executed by a processing device, cause the processing device to carry out an operation comprising: ingesting metadata associated with a first song including a plurality of first song lyrics; dividing the plurality of first song lyrics into corresponding lyric blocks; encoding, via a phonetic color-number pairing, each lyric block by determining a first consonantal sound of each lyric, associating the first consonantal sound with a predetermined color-number pairing, and color-coding a plurality of corresponding lyric blocks based on the predetermined color-number pairing; generating structured grids comprised of the corresponding color-coded lyric blocks and displaying the structured grids via client devices.

The present invention discloses a Japanese language input device, which includes a first portion for inputting consonants and a second portion for inputting vowels, and includes silent keys for displaying Japanese syllables in combination with the "a", "i", "u", "e" and "o" keys of the second portion. The Japanese language input device can be embodied by being included in a PC keyboard or a game keyboard.

The application discloses an input method, device and system based on number sequence final consonant definition and column direction mapping. The method comprises the following steps: according to the consistency principle of pronunciation tongue position, merging final consonants in the Chinese pinyin scheme into 11 groups of number sequence final consonants, establishing a column direction mapping relationship between the 11 groups of number sequence final consonants and 11 column character keys of a keyboard, so that the character final consonants on each column character key are merged into the corresponding number sequence final consonants through column direction compression; in response to the input operation of a user, converting the character final consonants into corresponding number sequence final consonant codes according to the mapping relationship, and generating a candidate word list. The application realizes single key triggering of final consonants by systematically merging final consonants into 11 groups and establishing a determined mapping with the column direction of the keyboard, solves the problems of multiple key strokes and inconsistent coding logic in the prior art, significantly improves the input efficiency of the Chinese pinyin, supports multiple input modes to share a unified coding system, and reduces the learning cost of users.

The invention provides a Chinese named entity recognition method based on Chinese character multi-feature fusion dictionary information, and the method comprises the steps: based on Chinese character, font and pinyin features, fusing dictionary information, constructing three character and word sequences, obtaining character embedding vectors of characters and words through table look-up, splitting the characters into basic parts, and splitting the words into synthesis parts of the characters. The method comprises the following steps of: extracting corresponding font embedding vectors by utilizing a convolutional neural network, converting characters into pinyin, converting words into initial and final consonants of the characters, extracting corresponding pinyin embedding vectors by utilizing the convolutional neural network, finally performing linear mapping on the characters, the font and the pinyin embedding vectors, and fusing relative position codes in corresponding character and word sequences. The method comprises the following steps: obtaining final character, font and pinyin feature vectors through an improved Transform model, splicing the feature vectors, carrying out linear mapping to obtain a fusion feature vector, and predicting an entity label type through a conditional random field. According to the scheme, the accuracy and efficiency of Chinese named entity recognition can be improved.

Disclosed in the present invention is an English word generation and reading platform, comprising a platform body and a word-formation carrier module and an electronic reading module that are installe

A method for providing information for laryngeal disease diagnosis according to an embodiment of the present disclosure may comprise the steps of: acquiring information on a diagnostic phrase uttered by a subject; and extracting information on a laryngeal disease of the subject on the basis of the information on the diagnostic phrase. The diagnostic phrase may include one syllable or two or more different syllables in which each syllable includes one consonant and one vowel, wherein: for each syllable, each consonant is selected from among a fricative sound and a nasal sound produced at the palate or the larynx; and the vowel is selected from among a vowel in which a first formant is located in the highest frequency band, a vowel in which a second formant is located in the highest frequency band, and a vowel in which an average of the frequency band of the first formant and the frequency band of the second formant is located in the lowest frequency band.

The invention relates to a hearing system (2) with a hearing instrument (4) to be worn in or at an ear of a user and a method for operating a hearing instrument (4). A sound signal (I) is captured from an environment of the hearing instrument (4) and processed to derive a processed sound signal (O) which is output to a user of the hearing instrument (2). Said processing includes applying a noise suppression algorithm by which speech peaks (SP) in each of which the captured sound signal (I) contains sound of a spoken consonant or a spoken consonant of a predefined consonant type are detected, and by which a noise suppression gain (gs) is applied to the captured sound signal (I) or a signal derived there-from, such that the processed sound signal (O) is attenuated to a noise suppression level outside said speech peaks (SP). Said processing also includes applying a consonant extension algorithm by which, at the end of each speech peak (SP), the signal level of the processed sound signal (O) is maintained or gradually reduced to the noise suppression level within a predefined extension time (Ts).

The invention discloses a teaching-aided speech analysis teaching audio evaluation method and system, and belongs to the technical field of speech processing. Teaching audio voice signals are segmented into a plurality of sub-segments through a sliding window, wavelet decomposition and reconstruction are carried out on each sub-segment, and low-frequency, medium-high-frequency and high-frequency components are obtained. On the basis of the time domain energy of the three components, consonant-vowel prominence, resonance intensity and voice massiveness are obtained, and a time domain feature vector is formed; obtaining low-frequency, medium-high-frequency and high-frequency energy dispersivity according to the energy dispersivity, and forming a frequency domain feature vector; and calculating a fluctuation coefficient through the time-frequency feature vectors of the adjacent sub-segments, and constructing time domain and frequency domain fluctuation vectors. And splicing the time-frequency feature vectors of the sub-segments into a matrix, extracting features, performing enhancement in combination with a fluctuation vector to obtain time-domain and frequency-domain enhanced features, inputting the time-domain and frequency-domain enhanced features into a dual-channel neural network, and finally outputting a teaching audio quality score. According to the invention, the teaching audio quality evaluation precision is improved.

The invention provides a pinyin input device, a pinyin input method and a computer program product, and the device comprises a keyboard module which is configured to have mapping of a first key and a key value; the initial consonant module is configured to have mapping of a second key and a key value, and the mapping of the second key and the key value is used for configuring the corresponding relation between the first letter group defined in the English letter set and the initial consonant key value group and the keys; the vowel module comprises a single vowel unit, a basic vowel unit and a derivative vowel unit; the syllable analysis module captures an input sequence generated by performing trigger operation on the keyboard, and analyzes the input sequence based on at least one of mapping of a second key and a key value configured in the initial consonant module and mapping of a third key and a key value, mapping of a fourth key and a key value and mapping of a fifth key and a key value configured in the final module; determining the initial consonant and vowel combination in the input sequence meeting the Chinese pinyin rule, and outputting words or phrases corresponding to the initial consonant and vowel combination.

To provide a pronunciation symbol display system, a pronunciation symbol display program and a voice output system for displaying pronunciation symbols capable of visually recognizing the image of a voice and suitably expressing various pronunciations.SOLUTION: In the symbol display section 21A, a plurality of graphic pronunciation symbols are displayed side by side, the graphic pronunciation symbols using consonant-oriented morphology symbols which are symbols imitating the morphology of the pronunciation organs and correspond to the articulation parts, vowel-oriented morphology symbols in which a component part representing the front-back position of the tongues by the position in the left-right direction and a component part representing the size of the gap from the upper jaw to the tongues by the position in the up-down direction are combined, and auxiliary symbols, and pronunciations output as voices can be represented by the graphic pronunciation symbols corresponding to the respective pronunciations.SELECTED DRAWING: Figure 2

The invention discloses an English pronunciation automatic labeling system and method based on a Webster dictionary, and relates to the field of computer-aided language learning. The method comprises the following steps: firstly, taking American phonetic symbols in a Merriam-Webster dictionary as an authoritative basis to obtain word standardized phonetic symbols; then, phonetic symbols are atomized and segmented into fixed phoneme sequences, and the fixed phoneme sequences are aligned with word letter sequences; the method is characterized in that letters are dynamically consumed through a vowel-letter mapping model and a consonant-letter mapping model on the basis of a double pointer alignment model, missing and redundancy in alignment are processed through a silence annotation mechanism and a sound adding annotation mechanism, and finally a word annotation result with phonemes and letters accurately aligned is generated; and on the basis, voice change labeling on the sentence level is carried out, and words and sentence labeling symbols are not overlapped. According to the method, complete phoneme-letter alignment labeling covering silence and sound adding conditions is realized for the first time, the pain point of sound-shape separation in the prior art is solved, the labeling complexity is remarkably reduced through unified and simplified design, and an efficient and clear pronunciation self-learning tool is provided for non-native language learners.

The application discloses an AI algorithm optimization-based sound recognition acceleration method, and particularly relates to the technical field of speech recognition, and comprises instantaneous audio frame composite feature extraction, dynamic inference configuration strategy generation, instantaneous reconstruction inference network construction, accelerated forward inference and decoding lattice generation, and optimal recognition text sequence output. The application dynamically specifies a macroscopic calculation path for a pickup input signal by calculating the instantaneous features of audio frames, and establishes shielding rules according to real-time speech speed. During inference, the network is instantaneously reconstructed according to the hierarchical regulation mechanism, shallow paths that skip the encoder layer are used for simple signals such as silence or vowels, and deep paths are called for complex consonants. The strategy double-binds the calculation resources and real-time features of signals, thereby significantly reducing the average calculation load and delay of a terminal device when processing real speech streams without sacrificing the processing capacity of complex signals.

Central nervous (“CNS”) health in subjects who have human immunodeficiency virus (“HIV”) or non-human-species analogs thereof is 102 evaluated or otherwise monitored by analyzing frequency following response (“FFR”). In general, one or more components of an FFR are analyzed, The FFR is measured in response to the administration of an acoustic stimulus to the subject. The acoustic stimulus includes a complex sound, which may include a consonant and a consonant-to-vowel transition. An indication of CNS health can be generated by measuring changes in the FFR components (e.g., over time or relative to normative data).

In non-limiting examples of the present disclosure, systems, methods, and devices for determining a language of a text string are presented. A language detection model can be maintained. The language detection model can include identities and weights for initial and final consonants, identities and weights for prefixes and suffixes, and identities and weights for vowel sequences, where each identity is derived from a training corpus. The weights can correspond to frequencies of the text units in the corpus. A text string can be received, and a match score between the text string and a language of the language detection model can be determined. The match score can be based on initial and final consonant scores, prefix and suffix scores, and / or vowel sequence scores for each word in the text string. If the match score satisfies a threshold, a subsequent action associated with the language can be performed.

The application provides a Chinese named entity recognition method based on Chinese character multi-feature fusion dictionary information, which is based on Chinese character features, character shape features and pinyin features, fuses dictionary information, constructs three word sequences, obtains character embedding vectors of words and characters through table lookup, splits words into basic components and splits words into synthetic components of characters, extracts corresponding character shape embedding vectors by using a convolutional neural network, converts words into pinyin, converts words into initial and final consonants and vowels of characters, extracts corresponding pinyin embedding vectors by using a convolutional neural network, finally linearly maps the character embedding vectors, character shape embedding vectors and pinyin embedding vectors, fuses relative position coding in corresponding word sequences, obtains final character feature vectors, character shape feature vectors and pinyin feature vectors by using an improved Transformer model, splices the feature vectors, linearly maps the feature vectors to obtain fusion feature vectors, and predicts entity label types by using a conditional random field. The application scheme can improve the accuracy and efficiency of Chinese named entity recognition.

The present disclosure provides a multi-functional speech recognition method, system and terminal. The present disclosure constructs an end-to-end speech recognition system with pinyin initial and final consonants as modeling units, and adds a modeling unit probability output module, effectively improving non-close sound character replacement errors, and relative to existing end-to-end speech recognition systems, adding various functions such as end-to-end speech recognition system acoustic recognition performance evaluation and pronunciation standard degree evaluation. The method comprises: receiving a speech to be recognized; performing acoustic feature extraction and encoding on the speech to be recognized; decoding the encoded acoustic features using a Chinese character decoder, wherein the Chinese character decoder uses pinyin initial and final consonants as modeling units, and maps the encoded acoustic feature sequence to a Chinese character sequence through initial and final consonants; and outputting a speech recognition result.

The invention discloses a Parkinson's disease dysarthria early recognition method based on voiceprint features, and belongs to the technical field of medical diagnosis. The method comprises the following steps: performing voice analysis and voice recognition on original voice data of a to-be-recognized object, extracting pronunciation deviation and an initial feature set related to voiceprint in a fragment, screening out target features with remarkable discrimination degree for recognition of dysarthria of Parkinson's disease, and obtaining a dysarthria recognition result of the to-be-recognized object through a model. Through accurate vowel and consonant fragment extraction and pronunciation deviation recognition, in combination with association of a character sequence and voice data, accurate interception of phoneme fragments is realized, quantitative judgment of pronunciation deviation is realized, key dimensions of dysarthria recognition are reserved through feature extraction, early signals of dysarthria of Parkinson's disease are captured, and the recognition accuracy of dysarthria of Parkinson's disease is improved. High-risk groups are marked, and an early warning result is calculated and output in combination with a joint risk value, so that the problem of unobvious symptoms in a prosperous period is solved, a review interval is dynamically adjusted, and whole-process management from identification to monitoring is realized.

The invention provides a method and a system for converting natural intonation into melody, a terminal and a medium, which are characterized in that fundamental frequency and tone length information of a voice sample are extracted, initial and final consonants are distinguished, fundamental frequency parameters of each final consonant are calculated, and the tone tuning range of each final consonant in a statement is determined. And matching music symbols by using the tuning ranges to generate a preliminary melody, and finally aligning the melody with the syllables of the voice sample to generate an audio file with a song melody. On the basis of the phonetic theory, the fundamental frequency, the tone length and the pause interval information of the voice sample are accurately extracted, and it is ensured that the generated melody can accurately reflect the characteristics and rhythm of natural intonations. The automatic method not only simplifies the operation process and improves the conversion efficiency, but also is suitable for a plurality of fields such as linguistics research, speech synthesis, language teaching, language training and pronunciation improvement.

The invention discloses a phonetic and morphological code Chinese character input method based on binary syllabification and initial consonants of head and tail components, belongs to the technical field of Chinese character input methods, and aims at solving the problems that an existing phonetic and morphological code input method is unreasonable in key position distribution, high in repeated code rate and too long in code length. The final key positions are mnemonic with the aid of final poems, are classified and distributed at 30 key positions according to final heads, and are combined with compound finals and the like; initial keys correspond to a standard English keyboard, V = zh, I = ch, U = sh, O is a zero initial, y and w are regarded as independent initial, and special keys reuse vowel keys. The initial consonants of radicals or strokes are taken by the head and tail parts, 201 radicals are adopted as the radicals, strokes are taken by non-radicals, the initial consonants of the radicals are taken by the head parts when a single character is the radicals, keys of part of the parts are adjusted, and auxiliary memorization is carried out by marking additional keys through visual elements. Common character codes are'initial consonants + final consonants + initial consonants of a first part + initial consonants of a tail part ', and the codes of words adopt different rules. The method has the advantages that no repeated code is added; the learning cost is low; the memory burden is relieved; the input efficiency is improved; and the repeated code rate is reduced.

The invention discloses a method and a system for generating a multi-dimensional voice training plan. The method comprises the following steps: firstly, collecting age, gender and voice samples of a patient, and obtaining seven-dimensional evaluation parameters including sound pressure, amplitude perturbation, maximum sounding duration, fundamental frequency perturbation, vowel space area, intonation damage and speech understanding degree score; and then, according to a preset logic, sequentially performing judgment based on the parameters, and dynamically combining different training modules of loudness, breath, pitch, vowel, gliding, tone, consonant and the like into a personalized voice training plan. Through multi-dimensional evaluation and dynamic module matching, the problem of training scheme solidification in the prior art is solved, and the individuation degree and rehabilitation effect of voice training are remarkably improved.

The present application relates to the technical field of speech evaluation, in particular to a pronunciation evaluation and scoring method based on deep learning.The present application uses a speech recognition model to recognize the true text result of the audio.Then an HMM-DNN model is used to obtain the posterior probability of the audio.Finally, a scoring model is used to score the phonemes.Before forced alignment, the speech recognition model is used to identify the correct text of the audio, avoiding the situation that the audio and the text are inconsistent and cannot be aligned to the correct position during the forced alignment process.Meanwhile, the scoring model is constructed using a deep neural network, which can fit multiple information such as posterior probability, initial and final consonants, part of speech, tone, pronunciation duration, etc., making the phoneme scoring more reasonable and more accurate.

The application discloses a Parkinson disease dysarthria early identification method based on voiceprint features and belongs to the technical field of medical diagnosis. The original speech data of a to-be-identified object is subjected to speech analysis and speech recognition, and an initial feature set related to voiceprints in a pronunciation deviation and a segment is extracted, target features with significant discriminability for Parkinson disease dysarthria identification are screened out, a dysarthria identification result of the to-be-identified object is obtained through a model, accurate vowel and consonant segment extraction and pronunciation deviation identification are realized, phoneme segment accurate cutting is realized by combining the association of a text sequence and speech data, the quantization determination of the pronunciation deviation is realized, the key dimension of the dysarthria identification is reserved through feature extraction, the early signals of Parkinson disease dysarthria are captured, the high-risk groups are marked, the early warning result is output in combination with the joint risk value calculation, the problem that the prodromal symptoms are not obvious is solved, the review interval is dynamically adjusted, and the whole-process management from identification to monitoring is realized.