35 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 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.

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 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.

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.

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 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.

The invention provides a visual symbol prompt-based language learning method, device and equipment and a storage medium, and the method comprises the steps: receiving an original language text, carrying out the recognition, decomposing each word in a recognition result into a letter sequence especially in an English language, recognizing the position attribute of each letter through a language database, and carrying out the recognition of the position attribute of each letter; vowel letters needing to be added with prompt pronunciation and consonant letters needing to be added with auxiliary spelling are distinguished. According to the specific positions of vowel and consonant letters in words and the combination environment of front and back letters, the mapping relation between the letters and standard pronunciation is established, and then a visual prompt symbol which is most matched with the pronunciation characteristics of the international phonetic symbol is selected from a symbol library of various mnemonic symbols. The visual prompt symbols are added to designated positions of corresponding vowels or consonants, and are recombined with unchanged letters to generate a novel coach type word with prompt pronunciation. The cognitive burden of English pronunciation learning is fundamentally reduced, and even a novel expression mode of language writing and description is led.

The invention discloses a dialect / accent universal conversion method and a dialect / accent universal conversion system based on double reference carriers and essential unit disassembly under the same language family, and relates to the technical field of language processing. According to the method, through positioning official standard pronunciation (pronunciation reference carrier) and legal standard characters (character reference carrier) of a target language family, differences between all dialects / accent and standard pronunciation are disassembled into three types of quantizable essential units of consonant mapping, vowel deformation and intonation / tone conversion, and a parameterized rule detailed rule template is generated; bidirectional conversion from standard to dialect and from dialect to standard is realized; and through global multilingual corpus closed-loop verification, marking exceptional pronunciation and iteratively optimizing the template, and ensuring that the conversion accuracy is greater than or equal to 95%. The system adopts a'modular + editable 'design, is internally provided with 10 + mainstream language family preset data, supports self-defined adaptation of small crowd language families / endangered dialects, and does not need to reconstruct a core algorithm. According to the method, the defects of poor universality, dependence on massive corpora and incapability of explaining in the prior art are overcome, efficient adaptation of all word families with unified characters and connected semantics in the world is achieved, and the method is applied to scenes such as language learning, cross-regional communication and dialect protection and has extremely high universality and practical value.

The present invention provides an input device and input method that can intuitively judge Japanese language through an input device such as a mobile phone or a computer vending machine and allow quick input using a method different from existing input systems. Disclosed is a Japanese character input device and the Japanese character input device comprises a first portion for inputting consonants and a second portion for inputting vowels, and comprises silent keys indicating Japanese syllables in combination with “”, “”, “”, “”, and “” keys in the second portion.

The invention relates to a learning evaluation method for English word pronunciation through audio recognition, which comprises the following steps: constructing a speech recognition system, preprocessing received user pronunciation audio, and then realizing phonetic symbol recognition of recognized words through vowel phonetic symbol recognition and screening and consonant phonetic symbol recognition and screening or full phoneme recognition. The word recognized by the final recognition phonetic symbol sequence obtained by the speech recognition system is compared with the stored standard pronunciation of the word, the pronunciation of the practicer is scored, and specific practice suggestions are given.

The invention discloses an intelligent voice recognition number query method and system based on an AI Agent. The method comprises the following steps: receiving user voice number searching information, converting voice into text, and extracting a user name; performing word segmentation processing on the user name; the AI Agent preferentially queries in a historical record library according to user name segmented words, and if a corresponding number exists, the number is output; if no corresponding number exists, inquiring step by step according to the same or similar sequence of names, pinyin and initial consonants based on user name word segmentation in a contact person information base, and outputting candidate numbers according to the basic matching degree; feeding back a queried number result to the user; and according to confirmation of the user on the number result, storing the log and updating the historical record library. Through user name word segmentation, multi-dimensional query in combination with a historical record library and a contact information library and dynamic updating of historical records based on feedback, Chinese character polyphone and front and back nasal sound recognition errors in speech recognition are effectively solved, and the number query accuracy is improved.

A speech 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 comprises an acoustic path comprising a vent, the acoustic path coupling the environment-facing portion with the ear canal-facing portion, and an electro-acoustic path comprising a microphone in the environment-facing portion, a filter, and a loudspeaker in the ear canal-facing portion. The acoustic path is arranged to transmit acoustic sounds in a vowel-dominant frequency range, and the electro-acoustic path is arranged to acoustically reproduce sound signals in a consonant-dominant frequency range and a vowel-dominant frequency range, the electro-acoustic path being arranged such that a signal-to-masking ratio is improved by the electro-acoustic path compensating for contributions from the acoustic path in the vowel-dominant frequency range. A method for enhancing speech intelligibility is further disclosed.

To accomplish an induced illusion phenomenon by a combination of vibrations, and to provide databases for trigger displacement, characteristics inducing stimulation and trigger stimulation, misunderstood (falsely perceived) vibration, synergetic effect relating to illusion, displacement structure regarding consonant and vowel, and illusion phenomenon.SOLUTION: In a tactile force information displaying system, a tactile force displaying device displays a stimulation by an object body or to the object body, and controls the stimulation applied to the object body in accordance with the operation by an operator, thereby generating tactile force. Next, at least one of the vibration, displacement, and deformation of the object body is displayed. A sense synthesizing and inducing device synthesizes the sensibility of inducing sensing, and generates at least one of contact force sense, kinesthetic sense, and illusion by displacement that gives sweep displacement to the object body.SELECTED DRAWING: Figure 8

The invention discloses a lip shape synchronous anthropomorphic control method and system for a high-simulation anthropomorphic robot. The method comprises the following steps: constructing a lip-shaped visual position mapping database of initial consonant phonemes and vowel phonemes; converting the pronunciation text into a pinyin sequence and identifying a pause symbol in the pinyin sequence; analyzing the pinyin into an initial consonant and vowel sequence, and extracting a corresponding lip action according to the mapping database; performing block processing on the action sequence according to the voice rhythm, and distributing the execution time of each action in combination with the audio duration; and a continuous lip shape control instruction sequence is generated by adopting a high-frequency interpolation mode, and is synchronously output in real time according to a time axis and audio playing. Through phoneme-level lip action driving, time fine distribution and continuous interpolation control, high consistency of voice content and lip actions in space and time dimensions is achieved, the anthropomorphic degree and the interaction reality sense of the humanoid robot in the language output process can be remarkably improved, and the user experience is improved. The lip-shaped driving system is suitable for various types of lip-shaped driving systems of humanoid robots.

The invention relates to the technical field of children phonetic system intelligent rehabilitation, in particular to a children phonetic system intelligent rehabilitation system based on an ICF framework, which comprises precise evaluation and rehabilitation training of 21 Chinese initial consonant phonemes, 17 phonetic system courses and rhythm functions, and through function evaluation, plan making, treatment implementation and curative effect evaluation. According to the invention, the rehabilitation mode can be set according to the type of the phonetic system disorder of the user, so that the rehabilitation treatment content and the rehabilitation steps are intelligently selected, the operation is simple and convenient, the treatment difficulty of the phonetic system disorder is reduced, and differentiated treatment schemes can be obtained according to different genders, different age groups and phonetic system damage degrees.

This specification provides a method, apparatus, and server for processing audio data, applicable to the financial field. Based on this method, after receiving target audio data and obtaining the corresponding first data group through speech recognition, the first data group is first split according to a preset splitting rule to obtain multiple character matrices. Then, based on the pinyin data of the characters, the characters in the character matrices are mapped to corresponding letter character combinations to obtain the corresponding first letter character matrix. According to a preset exchange rule, letter character combinations in the first letter character matrix that satisfy the exchange conditions are determined. The initial consonants and / or final vowels of the letter character combinations that satisfy the exchange conditions are then exchanged to obtain the corresponding second letter character matrix. Based on the second letter character matrix, the corresponding second data group is obtained. This method can efficiently hide relevant information carried in the audio data, protecting the data security of that information.