230 results about "Spoken language" patented technology

The invention relates to the technical field of artificial intelligence education, in particular to a Russian spoken language practice personalized recommendation method and system based on artificial intelligence, and the method comprises the steps: 1, outputting a phoneme sequence with a timestamp through Russian automatic voice recognition; 2, collecting an exercise interruption position and repeated read-after behavior data; 3, generating a dynamic learner portrait; 4, mapping high-frequency errors in the learner portrait into abnormal path weights of map nodes; 5, a lattice tail error option and a non-matching body verb interference item are injected; 6, when the voice fluency attenuation of the learner exceeds a dynamic threshold value, the sentence complexity is reduced; and 7, calculating an error rate descent gradient based on the exercise completion data, and dynamically adjusting the abnormal path weight of the knowledge graph. Through audio stream analysis and syntax tree construction, the system can accurately identify errors of the learner in grammar, pronunciation and other aspects, and the learning efficiency is improved.

Devices, systems, and techniques are disclosed that implement the training and deployment of automatic transcription-based translation systems using language models. The techniques include: processing, using a first speech-to-text (S2T) model, an initial input that includes spoken language in a first language to generate a transcription of the spoken language; and processing, using a second S2T model, a second input to generate a translation of the spoken language into a second language. The second input includes at least a representation of the spoken language and the transcription of the spoken language.

An estimation method includes: obtaining a first voice feature group of a plurality of persons who speak a first language; obtaining a second voice feature group of a plurality of persons who speak a second language; obtaining a voice feature of a subject; correcting the voice feature of the subject according to a relationship between the first voice feature group and the second voice feature group; estimating, from the voice feature of the subject that has been corrected, an oral function or a cognitive function of the subject by using an estimation process for an oral function or a cognitive function based on the second language; and outputting a result of estimation of the oral function or the cognitive function of the subject.

The invention discloses a spoken language evaluation method and device based on deep learning and a medium, and relates to the technical field of spoken language evaluation, and the method comprises the steps: collecting spoken language audio signals, carrying out the acoustic feature extraction of the spoken language audio signals through Mel-frequency cepstrum coefficient transformation, and generating an acoustic feature vector sequence; constructing a deep learning pronunciation diagnosis model, inputting the acoustic feature vector sequence into the deep learning pronunciation diagnosis model, calculating a multi-dimensional distance between each voice segment in the acoustic feature vector sequence and the phoneme prototype in a measurement space, and generating a pronunciation diagnosis result; converting the acoustic feature vector sequence into a text sequence through a speech recognition conversion method; and constructing a deep learning role analysis model, and inputting the text sequence into the deep learning role analysis model to generate a semantic role graph. According to the method, the acoustic deviation between the quantized speech segment and the standard phoneme in the measurement space is calculated through the phoneme prototype distance, and accurate space-time positioning and quantitative guidance of the pronunciation defect are realized.

An integrated development environment (IDE) for designing, programming, and configuring aspects of an industrial automation system uses a generative artificial intelligence (AI) model and associated neural networks to generate portions of an industrial automation project in accordance with functional requirements provided to the industrial IDE system in intuitive formats, such as spoken or written plain language text. The system uses generative AI to translate plain language requests or functional specifications into industrial control code, human-machine interface (HMI) applications, device configuration settings, or other aspects of an industrial control project.

The invention relates to the technical field of voice semantics, can be applied to business scenes of financial science and technology, medical health and the like, and discloses a sign language animation generation method, device, equipment and medium based on semantic parse. The sign language animation generation method comprises the steps that voice input is received and recognized as text content, field semantic parse is conducted on the text content to generate a field semantic template, and the field semantic template is used for generating a sign language animation; and converting the domain semantic template into a sign language intermediate representation sequence, generating a three-dimensional sign language action sequence based on the sign language intermediate representation sequence, rendering the three-dimensional sign language action sequence into a virtual image sign language animation, and displaying the virtual image sign language animation. According to the invention, by fusing speech recognition, semantic analysis and three-dimensional action rendering, direct conversion from spoken language content to sign language animation is realized, and a complete visual expression link from speech to sign language is formed, so that a user can intuitively understand the speech content in a sign language form through a virtual image, and the user experience is improved. Therefore, the barrier-free performance of human-computer interaction and the accuracy of information transmission are improved.

The invention belongs to the technical field of English teaching methods, and particularly relates to an intelligent English teaching method and system and a storage medium, and the method comprises the steps: constructing a multi-dimensional linguistic feature analysis model, and extracting lexical features, syntactic relationship features and semantic deviation features in a text input by a student through a natural language processing technology; dynamic student portraits are established based on the cognitive psychology theory, cognitive level labels are updated according to real-time learning data, and the data comprise grammar error clustering distribution, spoken language fluency indexes and vocabulary association response time; and generating a personalized teaching path, matching teaching materials from the hierarchical resource library according to the cognitive level label, and dynamically adjusting the complexity and presentation form of a teaching strategy. Lexical, syntactic and semantic deviation features are extracted through a natural language processing technology, student error types can be accurately positioned, the problem that traditional error correction only stays on surface modification is avoided, and cognitive tags are updated based on real-time learning data.

The invention provides a model training method, a written language spoken language conversion method, equipment and a product, which are applied to the field of natural language processing. The model training method comprises the steps that supervised training is conducted on a large language model based on first training data and task cues indicating to convert written languages into spoken languages, a supervised training model is obtained, and the first training data comprises supervised data pairs formed by written language texts and spoken language texts; based on second training data and a supervised training model, multiple rounds of reinforcement learning training are carried out, a written language spoken language model is obtained, and the second training data comprises a non-labeled written language data set and preference data used for generating reward signals. Therefore, the spoken language model of the written language is obtained by training after reinforcement learning of the large language model, and the quality of the spoken text transferred by the spoken language model of the written language is improved.

This invention discloses a spoken language understanding method based on multi-view expert fusion and interest lexical selection, belonging to the field of natural language understanding and semantic parsing technology. The method includes: extracting hidden state sequences from the input utterance using a shared encoder; constructing a multi-view expert fusion module containing utterance view experts, block view experts, and lexical view experts to generate multi-granularity expert features; generating intent aggregation features and slot aggregation features through a task decoupling gating mechanism; performing interest lexical selection on the intent aggregation features, calculating lexical importance scores, generating weighted intent representations, and predicting multi-intent labels; and inputting the slot aggregation features into a decoder with diagonal mask constraints to generate a position-aligned slot label sequence. This invention enhances the model's dynamic focusing ability on key intent signals and can be applied to intelligent dialogue systems, virtual assistants, and vertical domain semantic parsing scenarios.

Described herein are methods, systems, and media for supporting multi-language user sessions and fulfillments comprising: maintaining a repository of fulfillment objects each comprising a language and a region; establishing a user session with a user; determining a user region for the user in association with establishing the user session; identifying one or more fulfillment objects in the repository available for the user region; processing the user session, the user session comprising one or more user requests; applying a language detection model to each request to determine a user request spoken language; applying an understanding module to each request to recommend one or more of the fulfillment objects matching the region for the user; and rendering a response to each request to the user, utilizing the one or more of the fulfillment objects matching the region for the user, in the user request spoken language.

The application discloses a spoken language evaluation method and device, related equipment and a computer program product. The method comprises the following steps: obtaining the answer data of a testee, wherein the answer data comprises a question, the answer audio of the testee and a reference answer; identifying the answer text corresponding to the answer audio; obtaining the reasoning score of the testee by combining the answer text and the answer data and through a configured reasoning scoring model; obtaining a configured calibration model, wherein the calibration model is obtained by pre-training based on the answer text of a calibration testee, the reasoning score of the calibration testee and an expert score; the calibration testee is part of the testees participating in the current oral test; and obtaining the final score of each testee by using the calibration model to score according to the answer text and the reasoning score of each testee. Compared with the prior art which determines the score by simply calculating the similarity between the answer text and the reference answer, the oral evaluation result obtained by the application is more accurate.

The application provides a Chinese spoken language intention recognition brain-computer interface system based on a sound-meaning integration double model, belongs to the technical field of biomedical engineering, and relates to language brain-computer interface technology. Taking sound-meaning integration as the core, the stereotactic intracranial electroencephalogram (sEEG) technology is adopted to collect neural signals of the brain articulatory motor coding area and the semantic concept organization coding area. The system comprises a voice initiation decoder, a speech decoder, a semantic decoder and a Chinese word speech-semantic fusion synthesizer, the target decoder is constructed by extracting high gamma band features of key brain areas of the frontal lobe (left inferior frontal gyrus, premotor cortex, etc.), the temporal lobe (anterior temporal lobe, dorsolateral temporal lobe, etc.). At the same time, a visual and auditory induction training paradigm is matched, three tasks of listening to sound to group words, looking at words to group words and word association are set, and the subjects are supported to generate words independently. The system effectively solves the homonym and near homonym word ambiguity problem in Chinese spoken language recognition, and provides a precise interactive tool for ALS and other speech disorder patients.

A method includes receiving training data including a corpus of multilingual unspoken textual utterances, a corpus of multilingual un-transcribed non-synthetic speech utterances, and a corpus of multilingual transcribed non-synthetic speech utterances. For each un-transcribed non-synthetic speech utterance, the method includes generating a target quantized vector token and a target token index, generating contrastive context vectors from corresponding masked audio features, and deriving a contrastive loss term. The method also includes generating an alignment output, generating a first probability distribution over possible speech recognition hypotheses for the alignment output, and determining an alignment output loss term. The method also includes generating a second probability distribution over possible speech recognition hypotheses and determining a non-synthetic speech loss term. The method also includes pre-training an audio encoder based on the contrastive loss term, the alignment output loss term, and the non-synthetic speech loss term.

The invention provides a Chinese spoken language intention recognition brain-computer interface system based on pronunciation-meaning integration double models, belongs to the technical field of biomedical engineering, and relates to a language brain-computer interface technology. Sound-sense integration is taken as a core, and a stereotactic intracranial electroencephalogram (sEEG) technology is adopted to acquire neural signals of a brain phonetic motion coding region and a semantic concept organization coding region. The system comprises a sound production starting decoder, a voice decoder, a semantic decoder and a Chinese word voice-semantic fusion synthesizer, and a target decoder is constructed by extracting high gamma wave band characteristics of key brain regions of frontal lobe (left subfrontal gyrus, anterior cortex of motion and the like) and temporal lobe (anterior temporal lobe, dorsal lateral temporal lobe and the like). Meanwhile, an audio-visual induction training normal form is matched, three tasks of listening word combination, character reading word combination and vocabulary association are set, and subjects are supported to autonomously generate vocabularies. The system effectively solves the problem of ambiguity of homophonous and near-phonetic words in spoken Chinese recognition, and provides an accurate interaction tool for speech disorder patients such as ALS and the like.

The invention discloses an AI-based spoken language dialogue quality evaluation method, and relates to the technical field of artificial intelligence and natural language processing, and the method comprises the steps: receiving a spoken language dialogue audio stream, extracting text content information and acoustic rhythm information, carrying out the correlation fusion according to a timestamp, and generating a multi-mode dialogue data sequence; carrying out conjoint analysis on the dialogue logic relation graph and the dynamic memory bank, and calculating a dialogue structure consistency index to obtain a comprehensive quality evaluation score; and based on the comprehensive quality evaluation score and the dynamic memory library, positioning contradictory nodes and contexts in the dialogue logic relation graph, constructing a local consistency reconstruction task, and updating the memory enhancement neural network by using the local consistency reconstruction task. According to the method, the memory enhancement neural network is updated by using the local consistency reconstruction task, adaptive learning and sustainable evolution of the memory enhancement neural network based on actual dialogue contradictions are realized, and the consistency detection accuracy and the dynamic ability of adaptability are improved.

An integrated development environment (IDE) for designing, programming, and configuring aspects of an industrial automation system uses a generative artificial intelligence (AI) model and associated neural networks to generate portions of an industrial automation project in accordance with functional requirements provided to the industrial IDE system in intuitive formats, such as spoken or written plain language text. The system uses generative AI to translate plain language requests or functional specifications into industrial control code, human-machine interface (HMI) applications, device configuration settings, or other aspects of an industrial control project.

A method and apparatus for generating one or more differentiated oral prompts for learning, the method comprising: presenting a learning task to a user on a display; receiving user feedback on the learning task; determining a diagnostic input based on the user feedback; performing a diagnosis on the diagnostic input using a prompt generation model to generate differentiated oral prompts and differentiated speech emphasis masks associated with the differentiated oral prompts; inputting the differentiated oral prompts and differentiated speech emphasis masks to a text-to-speech module having prosodic control so as to generate an audio signal for reading a differentiated oral prompt having the speech emphasis specified in the differentiated speech emphasis mask, wherein the differentiated speech emphasis mask includes data indicating prosodic control; and converting the audio signal to a format for reading a differentiated oral prompt having the specified speech emphasis via an audio device.

Selecting music that complements spoken language, such as announcements, is a time-consuming task. [Solution] The sound source formation system 1 includes a word matching unit 10 that compares related words in the relational data with words in the sound-related information by referring to audio-related information containing multiple words and relational data in which music and related words are related; a keyword selection unit 20 that selects a keyword from the matching words that match through the matching of related words and words in the sound-related information by the word matching unit 10; a music selection unit 30 that selects music related to the keyword as selected music based on the keyword and relational data; a synthesis unit 40 that forms a sound source by synthesizing audio data related to the sound-related information and the selected music; and a range setting unit that sets the range for matching words in the sound-related information. The word matching unit 10 matches words in the sound-related information within the range set by the range setting unit.

The invention discloses an immersive family bilingual environment generation system and device, and the system builds an immersive bilingual learning environment through the closed-loop cooperation of an input end, a processing end, an output end and a feedback module. The input end comprises a microphone array, a UWB positioning module and a voiceprint registration unit, and is used for collecting voice and centimeter-level space coordinates and establishing member voiceprint files. And the processing end fuses acoustics and spatial data to realize sound source positioning and identity recognition, calls an online large model to carry out context completion and scene translation on spoken language, and synthesizes target voice with original speaker timbre based on a voiceprint file. And the output end performs directional playing through beam forming according to the position of the listener and provides multi-mode feedback. According to the invention, immersive interaction and adaptive learning that who speaks and translates like who are realized, and the problems that traditional equipment is rigid in interaction and breaks away from the context are solved.

1. Name of the product in this design: Oral English Practice Machine (English Learning). 2. Purpose of this design: To be used as a tool for correcting accents and practicing conversations during English speaking practice. 3. The key design feature of this product is its shape. 4. The image or photograph that best illustrates the design's key points: 3D view 1.

Implementations described herein relate to generating and rendering continuous content (e.g., natural language content) that may be used by a human user in completing a partial spoken utterance of the user.SOLUTION: The continuous content may be rendered via a wearable device (e.g., earphones or glasses). In various implementations, the generation and / or rendering of the continuous content may be performed automatically (at least when certain conditions are satisfied) in response to the partial spoken utterance and without relying on any user input that explicitly invokes the generation and / or rendering. Further, in many implementations, at least rendering of continuous content is selectively performed. For example, automatic rendering of continuous content may be selectively implemented when certain conditions are met, such as detection of disfluency following a partial spoken utterance.SELECTED DRAWING: Figure 4

The invention discloses an ultrasonic report generation method, related equipment and a computer program product, and relates to the technical field of artificial intelligence. According to the method, streaming recognition is performed on the real-time spoken voice of the doctor in the ultrasonic detection process of the doctor, the current voice transcription text fragment is obtained, the large model is called to extract the ultrasonic detection parameters in the current voice transcription text fragment in a fast thinking mode, and the extracted ultrasonic detection parameters are output and previewed in real time, so that the accuracy of ultrasonic detection is improved. Therefore, real-time interaction with doctors is generated, and the result of the detection process is transparent to the doctors. After ultrasonic detection is finished, a large model is called to generate ultrasonic description and diagnosis based on an original complete voice transfer text in a slow thinking mode, ultrasonic detection parameters, the ultrasonic description and diagnosis are integrated to obtain a high-quality ultrasonic report, the clinical requirement of real-time interaction is met, the clinical working efficiency is improved, and the clinical experience is improved. And the quality of the finally obtained ultrasonic report can be ensured.

The application provides a spoken-to-written conversion method and device based on reinforcement learning, equipment and medium, wherein the method comprises: obtaining a spoken text; inputting the spoken text into a conversion model to obtain a written text output by the conversion model; the conversion model is obtained by reinforcement learning, taking the editing operation of each word in the sample spoken text as an action, and taking the semantic consistency between the sample written text obtained by performing the editing operation and the sample spoken text and / or the written degree of the sample written text as a reward. The method, device, equipment and medium provided by the application break the limitation of insufficient labeled data in the process of reinforcement learning, and the semantic consistency and written degree give high-level and interpretable rewards. The conversion model obtained by application of the conversion model ensures the reliability and interpretability of the conversion from spoken text to written text.

The invention provides a spoken language fluency evaluation method based on pronunciation fluency and cognitive fluency, which is applied to the technical field of spoken language evaluation and artificial intelligence and comprises the following steps: acquiring voice audio of a to-be-tested person completing a target task; performing index calculation on the voice audio to obtain pronunciation fluency and cognitive fluency; performing weighted calculation on the pronunciation fluency and the cognitive fluency to obtain a spoken language fluency evaluation result of the to-be-tested person; wherein the pronunciation fluency is used for quantifying the surface fluency of the spoken language; the cognitive fluency degree is used for quantifying the cognitive fluency of spoken language. According to the invention, the defect that a traditional spoken language fluency evaluation method only pays attention to a single dimension is overcome; the evaluation process can accurately reflect the pronunciation fluency and the cognition fluency of the person to be tested, and the practicability and effectiveness of spoken language fluency evaluation are improved.

The disclosure relates to a method for enhancing a generative spoken language model. The method comprises obtaining at least one non-semantic feature including prosodic information of original speech data by computing a difference between an encoded unit sequence of the original speech data and an encoded unit sequence of normalized speech data; encoding said at least one non-semantic feature to produce a quantized representation of the at least one non-semantic feature; and inputting the quantized representation and discrete phoneme-related units into a deep learning model to generate a speech sequence representing the discrete phoneme-related units and the at least one non-semantic feature.

The utility model relates to a spoken language sound receiving equipment with dustproof function, including the casing of spoken language sound receiving equipment, is equipped with the pickup hole on the casing, is equipped with the dust screen in the casing, and the dust screen covers the pickup hole, is equipped with the dust cover on the casing, and the dust cover is located on the casing, is equipped with a plurality of through -hole on the dust cover, and the movement track of through -hole and the movement track of pickup hole intersect, the utility model discloses a dust cover rotates on the casing, through the through -hole and the pickup hole overlap or stagger, to open or close the pickup hole, and then prevent dust through the pickup hole and enter the spoken language sound receiving equipment in the idle state, simple and efficient, safe and reliable.

To provide a system and method for performing utterance language understanding with fewer computing resources.SOLUTION: A computer implemented method for carrying out utterance language understanding executes: receiving data representing audio including a voice; processing data using a model for determining a text corresponding to a content of the voice; receiving input for carrying out a language understanding task including a presentation based on a text of one or more semantic labels; processing input using at least a portion of the model to extract semantic information from the text corresponding to the content of the voice; and acquiring the semantic information extracted in connection with the language understanding task.SELECTED DRAWING: Figure 1

Implementations described herein relate to various techniques for biasing interpretations of verbal utterances received in a vehicular environment. For example, implementations may receive a verbal utterance including a query from a user of a vehicle and obtain corresponding vehicle sensor data instances generated by a vehicle sensor(s) of the vehicle. Some implementations may determine to perform a search only on the first corpus data and not on the second corpus data to obtain a given response to the query based on various criteria, which may include at least the query, the corresponding vehicle sensor data instances, corresponding timestamps associated with the corresponding vehicle sensor data instances, and / or corresponding durations the user is associated with the vehicle. Additional or alternative implementations may perform a search on both the first corpus data and the second corpus data to obtain a given response based on the criteria.

This invention discloses a text pronunciation optimization method and system for speech synthesis, belonging to the field of speech synthesis management technology. In this method, after emotional processing, long sentences are split into segments based on a triple rule system of semantic blocks, classical Chinese function words, and character length. The English portion of the text undergoes layered processing, distinguishing between pure uppercase letter combinations and regular English words, adding splitting and prosodic markers to pure uppercase letter combinations, and generating optimized text pronunciation information. This invention breaks through the limitations of existing single-rule adaptation in speech synthesis text processing, pioneering a multi-dimensional layered optimization framework that integrates technologies such as semantic parsing of numbers and operators, scene-based matching of polyphonic characters, emotional markers for literary texts, and semantic long sentence splitting. It designs multiple exclusive optimization rules for the speech synthesis and reading needs of literary and everyday spoken texts, solving the core pain point of existing technologies that emphasize generality but neglect specific scenarios.

A content broadcast system may allow a user to select and start an audio stream of desired audio content without having to connect and authenticate to a specific device. Rather than a user having to pause the content and reconfigure settings of the broadcast system to select the desired audio content, the system may broadcast advertisements listing available audio content (e.g., corresponding to different spoken languages) and actively listen for requests from a device for new audio content to be streamed with the content. A user may manually select the new audio content, or the listening device may request particular audio content based on user preferences (e.g., a preferred language for streaming content). The system may broadcast audio data using a Bluetooth protocol.