Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

15468 results about "Speech recognition" patented technology

Speech recognition is a interdisciplinary subfield of computational linguistics that develops methodologies and technologies that enables the recognition and translation of spoken language into text by computers. It is also known as automatic speech recognition (ASR), computer speech recognition or speech to text (STT). It incorporates knowledge and research in the linguistics, computer science, and electrical engineering fields.

Context LLM response system

A computing device can receive a first conversational input of one or more sequential conversational inputs via one or more user input devices. The first conversational input can be associated with a particular uniform resource locator (URL) address. The computing device can process the first conversational input using one or more natural language processing algorithms to determine one or more intents based on the first conversational input. The computing device can select one or more data segments from a data store based on the intents. The computing device can generate a command including the data segments. The computing device can generate a generative response by performing the command with a generative artificial intelligence algorithm. The computing device can provide a response to the first conversational input based on the generative response.
Owner:SATISFI LABS INC

Assistant System Using Multimodal Multitask Medical Machine-Learned Models to Perform Image Processing to Answer Natural Language Queries

An example assistant system can use a multimodal multitask medical machine-learned model to perform image processing to answer natural language queries. A device can process speech data or other natural language inputs to obtain a query. The query can be processed alongside image data that provides context for the query. The example system can receive a query associated with a particular task domain; generate, based on the query, a query input that comprises query instruction data from a first modality and query context data from a second modality; generate a combined input comprising the query input and an exemplar input, wherein the exemplar input comprises exemplar instruction data from the first modality and an exemplar context placeholder in lieu of exemplar context data from the second modality; process the combined input with a multimodal machine-learned model to generate output data; and output a query response based on the output data.
Owner:GOOGLE LLC

Structure fatigue damage identification method based on acoustic emission and deep learning

The invention relates to the technical field of structural health monitoring and intelligent diagnosis, in particular to a structural fatigue damage identification method based on acoustic emission and deep learning, and the method comprises the steps: collecting a structural response signal under a fatigue load through an acoustic emission sensor array, inputting the structural response signal to a CNN-BiLSTM-Attention mixed deep learning model, and carrying out the recognition of the structural fatigue damage through the CNN-BiLSTM-Attention mixed deep learning model; the model extracts local time domain features through a dynamic adaptive convolution kernel, captures long time sequence dependence by using a bidirectional long-short-term memory network, focuses key damage features through a bimodal space-time attention mechanism, divides damage stages based on a nonlinear dynamic threshold algorithm of fracture opening amount, constructs a training data set of physical-data fusion, and performs dynamic time domain feature extraction. The learning rate is optimized by adopting a gradient sensitive cosine annealing algorithm, and the robustness of the model is improved in combination with an anti-noise and anti-loss function. The method integrates physical characteristics and an intelligent algorithm, and has the advantages of adaptive noise suppression, strong cross-domain generalization ability, high real-time performance and the like.
Owner:FUJIAN UNIV OF TECH

Feature information extraction method and system of sleep state monitoring model

The invention relates to the technical field of sleep aiding, in particular to a method and a system for extracting feature information of a sleep state monitoring model. The method comprises the following steps: carrying out multi-mode physiological signal acquisition on a detected object to obtain original sleep monitoring data; performing noise removal and signal enhancement processing on the original sleep monitoring data, and performing signal segmentation to obtain multi-channel sleep signal fragment data; performing feature extraction based on electroencephalogram, eye movement diagram, electromyogram, electrocardiogram and accelerometer signals on the multi-channel sleep signal fragment data to obtain multi-dimensional feature data; and performing ultrasonic feature and acoustic feature extraction on the multichannel sleep signal fragment data to generate acoustic feature data. According to the method, dynamic modeling and trend prediction are carried out on the conversion process of the sleep state, potential sleep disorder events can be accurately recognized, influence evaluation is carried out on the potential sleep disorder events through deep learning, and support is provided for personalized sleep diagnosis.
Owner:THE FIRST AFFILIATED HOSPITAL OF NAVAL MEDICAL UNIVERSITY OF CHINESE PEOPLES LIBERATION ARMY

Model cue word automatic optimization method and device, equipment and storage medium

The invention relates to an automatic optimization method for a model cue word, which comprises the following steps of: acquiring an initial cue word and a corresponding training data set which comprises input data and a corresponding real label; and then, inputting the initial cue word and the input data into a target model together to generate a corresponding prediction label. And on the basis, guiding a target model by using a feedback prompt word, and generating language prompt feedback by comparing the predicted tag with the real tag. The feedback is used for identifying potential defects in the initial cue word, optimizing the initial cue word based on the feedback, and finally generating a target cue word. The cumbersome process of manually adjusting the cue words is reduced, gradual improvement of the cue words is achieved through a feedback mechanism, and high accuracy and consistency of model output are ensured.
Owner:PING AN TECH (SHENZHEN) CO LTD

Detection of an audio deep fake and non-humans speaker for audio calls

A computer implemented system for authenticating an audio conversation occurring between a human target and an unknown speaker. The system adjusts messages sent to the speaker to include characteristics that evoke different responses in bots controlling vocoders to generate deepfakes than are evoked in humans. By analyzing these responses, harms from deepfake threats can be avoided by turning the tools used by deepfake generating bots against those very bots.
Owner:RED BEND LTD

Electrical audio signal processing systems and devices

According to an aspect of the present invention, there is provided an electrical audio signal processing system and device, comprising: a computer graphics processing and selective visual display system with a screen; an eye tracking device; a processor; one or more computer memory devices; wherein the processor is arranged for operations comprising: measuring the user's eye movements to ascertain the specific word on which the user is fixated, by the eye tracking device; modifying the display at the user's current fixation point; applying a delay between the presentation of successive graphic elements based on the user's calculated rate to accommodate the user's required time; and presenting elements to the user at a rate based upon the user's required time.
Owner:DECHARMS RICHARD CHRISTOPHER

Audio noise reduction method, device and system based on deep learning

The invention relates to an audio noise reduction method, device and system based on deep learning, and the method comprises the steps: obtaining an input audio signal with noise, and carrying out the multi-scale time-frequency decomposition, and obtaining a mixed time-frequency feature and a noise fingerprint spectrum; performing parameter parallel processing on the noise fingerprint spectrum through a preset dynamic kernel generation network, and performing preliminary noise reduction processing on the mixed time-frequency characteristics to obtain noise-reduced mixed data; performing dual-path processing structure construction on the noise reduction mixed data to obtain amplitude optimization data and phase optimization data; performing dynamic time-frequency domain cross fusion on the amplitude optimization data and the phase optimization data to obtain fused audio data; and carrying out differentiable acoustic equation constraint adversarial training on the fused audio data, and carrying out inverse time-frequency transformation processing to obtain a target noise-reduced audio signal. According to the invention, the overall efficiency and effect of audio signal processing can be effectively improved.
Owner:DONGGUAN HUAZE ELECTRONIC TECH CO LTD

High-expressive-force audio generation method based on natural language description text

A high-expressive-force audio generation method based on a natural language description text comprises the steps that S1, a pre-training multi-language text encoder is used for encoding an input natural language description instruction, and semantic information is extracted; s2, with text coding representation as a condition, semantic unit sequences of the audio are sequentially predicted through an autoregression model (AR), and the semantic unit sequences represent content event information appearing in the audio; s3, taking the text coding representation and the audio semantic unit sequence output in the S2 as a prefix condition, predicting a coarse-grained acoustic unit sequence of the audio through AR, and determining the overall duration and basic acoustic information of the audio; s4, predicting a fine-grained acoustic unit sequence of the audio by using a non-autoregressive model (NAR), and modeling audio detail representation and high-frequency information; and S5, inputting the multi-layer acoustic unit sequence into a vocoder to generate a high-quality audio waveform. The method directly supports the generation of the audio by a sentence of natural language description instruction, and improves the naturalness, expressive force and controllability of the generated audio.
Owner:TSINGHUA SHENZHEN INTERNATIONAL GRADUATE SCHOOL +1

Redacting portions of text transcriptions generated from inverse text normalization

Portions of text data generated from inverse text normalization may be redacted. Text data for redaction may be obtained. One or more inverse text normalization models may be applied to the text data to generate normalized text data. A machine learning model, trained to recognize text for redaction, may be applied to identify portions of the normalized text data for redaction. The identified portions may be redacted and the redacted normalized text provided to a destination.
Owner:AMAZON TECH INC

Audio generation model training method and device, computer equipment and storage medium

ActiveCN119132271Agenerate natureaccord with auditory perceptionSpeech synthesisFeature vectorEngineering
The invention relates to the technical field of machine learning, and discloses an audio generation model training method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring to-be-trained data, wherein the to-be-trained data comprises audio data, first data and second data; fusing the first data and the second data to obtain third data; an input layer of the multi-modal model is used for receiving audio data, first data and third data and outputting an audio residual vector quantization code, a first code corresponding to the first data and a second code corresponding to the third data, and a cross attention layer of the multi-modal model is used for fusing the first code, the second code and the audio residual vector quantization code; and obtaining a weighted audio feature vector. And training the multi-modal model to obtain an audio generation model. Therefore, the model can learn semantic and acoustic features of long texts and contexts, so that audio output which is more natural and more melodious and more conforms to inherent semantic and auditory perception features is generated.
Owner:PING AN TECH (SHENZHEN) CO LTD

Multi-task and multi-lingual emotion mismatch detection for automated dubbing

Methods and apparatus are described for evaluating dubbing of media content. Emotions are identified based on combinations of attributes determined for segments of a source language audio and a dubbed audio. The emotions may be compared to determine emotional prosody transfer between the source audio and dubbed audio. Based on the comparison, a notification is generated indicating whether an emotion classification associated with the source audio matches an emotion classification associated with the dubbed audio.
Owner:AMAZON TECH INC

Cable vibration signal feature extraction and mode recognition method and cable maintenance method

The invention relates to the technical field of signal processing, in particular to a cable vibration signal feature extraction and mode recognition method and a cable maintenance method. The cable vibration signal feature extraction method comprises the following steps: S1, collecting vibration data along a cable in a differentiated state, and dividing data grades according to signal strength to obtain an optimized compressed data set; s2, segmenting the optimized compressed data set according to a signal change frequency to generate a segmented compressed signal set; s3, based on the segmented compression signal set, key time point extraction is carried out, feature mapping is established, and time frequency feature mapping is obtained; and S4, performing abnormal signal feature point identification through time-frequency feature mapping, recording the time and the frequency band where abnormal features are located, and generating an abnormal signal feature library. According to the method, the abnormal information can be identified more quickly and accurately, the prediction capability of potential abnormity is enhanced, and more targeted maintenance and prevention measures can be formulated.
Owner:CHONGQING TAISHAN CABLE CO LTD

Gesture recognition method and device, medium, equipment and vehicle

The invention provides a gesture recognition method and device, a medium, equipment and a vehicle, and relates to the field of data processing. According to the method, firstly, diversified gesture image data of different sources and different scenes are collected to form a sample set; then, a lightweight dynamic gesture recognition network is constructed based on an actual application scene, the lightweight dynamic gesture recognition network comprises a deep separable convolution module, a feature pyramid module and a long-short term memory module, and the dynamic gesture recognition network is trained by using a diversified sample set; according to the method, the feature extraction capability is maintained through depth separable convolution, meanwhile, the complexity of the network is reduced, overall structure information and local detail information of gestures are fused through a feature pyramid module, spatial-temporal features of the gestures are learned through a long-short term memory module, and then different gesture actions are recognized. And finally, deploying the trained dynamic gesture recognition network in an actual application scene to perform real-time gesture recognition, thereby improving the accuracy and efficiency of gesture recognition.
Owner:CHONGQING CHANGAN AUTOMOBILE CO LTD

System and method to review online violence and education

A computing system is configured to obtain a video that includes text elements and visual elements. The computing system is further configured to generate a plurality of text tokens representative of audio spoken in the video and a plurality of frame tokens representative of one or more frames of the video. The computing system is further configured to generate a set of features that includes a text feature, a frame feature, and a multi-modal feature, wherein the multi-modal feature is representative of multi-modal elements of the video, and wherein generating the set of features is based on the plurality of text tokens and the plurality of frame tokens. The computing system is further configured to associate the set of features with one or more labels to generate a multi-label classification of the video. The computing system is further configured to output an indication of the multi-label classification of the video.
Owner:SRI INTERNATIONAL

Intelligent audio test system frequency response analysis method, device and equipment

The invention relates to the technical field of audio testing, and discloses an intelligent audio testing system frequency response analysis method, device and equipment, and the method comprises the steps: carrying out the audio parameter initialization of an intelligent audio testing system, and obtaining a testing parameter matrix and an excitation signal; performing dual-channel acquisition and time-frequency feature extraction to obtain a time-frequency feature data set; executing double-branch processing of time domain noise reduction and frequency domain enhancement to obtain a purified feature data set and a feature weighting matrix; performing segmented recursive calculation and feature aggregation to obtain a frequency response feature vector; decomposing the frequency response feature vector according to a test frequency band, and performing environment compensation and nonlinear calibration to obtain a standard frequency response data set; and inputting the standard frequency response data set into the deep neural network for feature recognition and mode classification to obtain a frequency response curve and a phase characteristic curve, thereby improving the test precision, the anti-interference capability, the automation degree and the adaptability of the intelligent audio test system.
Owner:SHENZHEN DEWEI AUDIO CO LTD

Multimodal deepfake detection via lip-audio cross-attention and facial self-attention

A novel multi-modal audio video framework is disclosed. The framework advantageously leverages both audio and video information to accurately detect whether the video has been manipulated, e.g., detect whether the video is a so-called ‘deepfake.’ In a video-only pipeline, the framework adopts a vision encoder having a feature extractor and a Transformer encoder that leverages self-attention mechanisms to detect artifacts in a facial region of the video. Additionally, in a separate audio-video pipeline, the framework adopts an audio+lip encoder having a Transformer encoder that leverages cross-attention mechanisms to identify discrepancies between lip movements of the person and words spoken by the person in the video. These two modalities are used jointly to make an inference as to whether the video has been manipulated.
Owner:PURDUE RES FOUND

Frequency-aware masked autoencoders for multimodal pretraining on frequency-based signals

The subject technology provides frequency-aware masked autoencoders for multimodal pretraining on frequency-based signals. An apparatus receives input data comprising frequency-based signal information associated with one or more modalities. The apparatus transforms the input data from a time domain to a frequency domain. The apparatus generates a frequency-embedded latent representation of the input data comprising time-domain and frequency-domain information. The apparatus also generates a masked frequency-embedded latent representation by masking one or more frequency components in the frequency-embedded latent representation. The apparatus produces a trained machine learning model by training a neural network to predict one or more masked frequency components of the frequency-embedded latent representation.
Owner:APPLE INC

Automatic Dubbing: Methods and Apparatuses

Automatic video dubbing methods and apparatuses automatically dub a video signal into a different target language than the original while controllably preserving vocal characteristics of original speakers in the corresponding audio, based on separating audio from the video, preserving audio timings, separating voice and non-voice segments from background noise, and using ASR, MT and signal processing techniques to generate properly sized and selectable speech translations into different languages corresponding to speaker voices in the video and emotions, voice and / or textual characteristics.
Owner:APPL TECH APPTEK

Method and system of automatic microphone selection for multi-microphone environments

A computer-implemented method of audio processing comprises receiving, by at least one processor, multiple audio signals from multiple microphones. The audio signals are associated with audio emitted from a same source. The method also may include determining an audio quality indicator of individual ones of the audio signals using a neural network, and selecting at least one of the audio signals depending on the audio quality indicators.
Owner:INTEL CORP

Real-time video translation and audio and picture synchronization method and system based on multi-modal large model

The invention provides a real-time video translation and audio and picture synchronization method and system based on a multi-modal large model, and relates to the technical field of video translations, and the method comprises the steps: obtaining a source video; extracting the source video based on the multi-modal large model to obtain a multi-modal feature; fusing the multi-modal features through a cross-modal attention mechanism to generate a context semantic vector; translating into a target language text in real time based on the context semantic vector, and processing the translated language text based on the multi-modal features to obtain a translated language sound source; and performing mouth shape adjustment on the source video based on the translation language sound source, and merging the translation language sound source and the mouth shape animation video to obtain a real-time translation video with synchronous sound and picture. According to the method, the limitation of traditional single-modal translation is broken through, and the semantic accuracy of translation is remarkably improved by dynamically aligning the context information through the multi-modal features in combination with a cross-modal attention mechanism.
Owner:SHANGHAI YINGZHUO INFORMATION TECH CO LTD

Audio coding and decoding method and device based on neural network, equipment and storage medium

The invention relates to the technical field of audio coding and decoding, and discloses an audio coding and decoding method and device based on a neural network, equipment and a storage medium. The method comprises the following steps of: firstly, gradually quantizing residual information of an audio signal by introducing an improved residual vector quantization method, and more finely retaining audio characteristics in a compression process; then, a loss function fusing reconstruction loss, perception loss, residual vector quantization loss and commitment loss is adopted, so that the reconstruction quality of the audio signal under different bit rates is remarkably improved, and efficient audio compression can be realized while high tone quality is ensured; and finally, an entropy coding module is introduced after quantization, so that the code rate of coding is further reduced, and the bandwidth requirement of audio real-time transmission is remarkably reduced.
Owner:JIHUA LAB

Cross-modal training of a machine-learning model that identifies abuse in audio streams

A metaverse application receives a user-provided audio stream associated with a user. The metaverse application obtains portions of one or more audio streams. The metaverse application divides the user-provided audio stream into a plurality of portions, wherein each portion corresponds to a particular time window of the audio stream. The metaverse application providing the plurality of portions of the user-provided audio stream as input to an audio machine-learning model. The audio machine-learning model outputs, based on the portions of the user-provided audio stream, a determination of abuse in a particular portion of the plurality of portions. The metaverse application performs a remedial action responsive to the determination of abuse in the particular portion.
Owner:ROBLOX CORP

Utilizing a large language model to generate an automated communication flow

A natural language description of a desired function to be achieved using an automated communication flow is received. A prompt template specifically for a communication channel is selected based on an analysis of the natural language description of the desired function to be achieved. A prompt for a large language model is automatically generated based on the natural language description, including by inserting at least a portion of the selected prompt template in the automatically generated prompt. The automatically generated prompt is provided to the pre-trained large language model. Based on an output of the large language model, an automated communication flow to be implemented for the communication channel is automatically generated.
Owner:MANYCHAT INC

Audio parameter adjusting method, apparatus and device, and storage medium

Disclosed are an audio parameter adjustment method, an audio parameter adjustment apparatus, an audio parameter adjustment device and a storage medium. The method includes: obtaining a target audio effect of an audio system, and analyzing the target audio effect to obtain a corresponding audio metric parameter; determining a target environment where the audio system is currently located, and calculating an environmental optimization parameter of the target environment; calculating, based on the audio metric parameter and the environmental optimization parameter, an optimization parameter of the audio system; and performing adaptive adjustment on the audio system based on the optimization parameter of the audio system.
Owner:LINKPLAY TECHNOLOGY INC

Prompt word optimization method and device, equipment, medium and product

The invention provides a cue word optimization method and device, equipment, a medium and a product, and the method comprises the steps: obtaining at least one first cue word related to a target business, and obtaining a business data sample set related to the target business; for each first cue word in the at least one first cue word, executing the following steps: acquiring a first evaluation result of the first cue word on a business data sample set, and determining error sample information corresponding to the first cue word based on the first evaluation result; sending a target cue word used for optimizing the first cue word to a first language model; and obtaining a second cue word output by the first language model. In the method, aiming at the cue word to be optimized, the task processing effect of the cue word in a business data sample set is evaluated, the cue word is optimized by combining related information of an error data sample and utilizing a language model, the cue capability of the optimized cue word in a target business is improved, and the cue effect of the cue word is optimized.
Owner:BEIJING ZITIAO NETWORK TECH CO LTD

Information handling system speaker identification to set audio drive settings

A portable information handling system speaker mount has standardized contacts and mounting points to accept plural speaker types with different speaker characteristics to generate audible sounds driven by an audio subsystem with audio driver settings, such as speaker-type gains. When a speaker is inserted, the audio subsystem communicates a coil characterization signal to the speaker and then analyzes the coil response to identify the type of the speaker, such as by determining the resistance of the coil to a direct current signal or the impedance of the coil from a frequency-based signal. In one example embodiment, the coil characterization signal generates audible noise from the speaker that is detected by a microphone and analyzed to determine the speaker type identity.
Owner:DELL PROD LP