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

2648 results about "Utterance" patented technology

In spoken language analysis, an utterance is the smallest unit of speech. It is a continuous piece of speech beginning and ending with a clear pause. In the case of oral languages, it is generally, but not always, bounded by silence. Utterances do not exist in written language, however, only their representations do. They can be represented and delineated in written language in many ways.

Machine operation assistance using language model-augmented perception

Various embodiments of the present disclosure relate to operator assistance based on extracting natural language characters from one or more sensed objects. For instance, particular embodiments may generate a natural language utterance based on extracting natural language text in a nearby traffic sign. In an illustrative example, particular embodiments may detect, via object detection and within image data, one or more regions of the image data depicting the traffic sign. Particular embodiments can then extract one or more first natural language characters represented in the traffic sign based at least on performing optical character recognition within the one or more regions of the image data in response to detecting the one or more regions of the image data depicting the traffic sign.
Owner:NVIDIA CORP

Virtual conversational companion

Techniques for rendering visual content, in response to one or more utterances, are described. A device receives one or more utterances that define a parameter(s) for desired output content. A system (or the device) identifies natural language data corresponding to the desired content, and uses natural language generation processes to update the natural language data based on the parameter(s). The system (or the device) then generates an image based on the updated natural language data. The system (or the device) also generates video data of an avatar. The device displays the image and the avatar, and synchronizes movements of the avatar with output of synthesized speech of the updated natural language data. The device may also display subtitles of the updated natural language data, and cause a word of the subtitles to be emphasized when synthesized speech of the word is being output.
Owner:AMAZON TECH INC

Training and using a deep learning model for transcript topic segmentation

The disclosure herein describes using a deep learning model to identify topic segments of a communication transcript. A communication transcript including a set of utterances is obtained. The set of utterances is divided into a plurality of utterance windows, wherein each utterance window of the plurality of utterance windows includes a different subset of utterances of the set of utterances, and wherein each utterance of the set of utterances is included in at least one utterance window of the plurality of utterance windows. For each utterance window of the plurality of utterance windows, each utterance in the utterance window is classified as a topic boundary or a non-boundary using a deep learning model. Topic segments of the communication transcript are identified based on utterances of the set of utterances that are classified as topic boundaries. A communication transcript summary is generated using the communication transcript and the identified topic segments.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Using facial movements to generate a conversational record

Systems, methods, and computer program products are disclosed for generating a common record based on differing source inputs. Generating a common record based on differing source inputs may include receiving via at least one sensor first non-audible signals indicative of verbalization of an individual; interpreting first words of the individual at least in part using the first non-audible signals received from the at least one sensor; receiving second signals generated by a source other than the individual; performing speech recognition on the second signals to interpret second words from the source; and using the first words and the second words to generate a record.
Owner:APPLE INC

Customer service verbal skill quality inspection result determination method and device, equipment, medium and product

The invention provides a customer service talk skill quality inspection result determination method and device, equipment, a medium and a product, and belongs to the technical field of artificial intelligence. Determining customer service verbal skills, user verbal skills and target standard verbal skills corresponding to the customer service verbal skills according to the conversation interaction voice data, and inputting the customer service verbal skills, the user verbal skills and the target standard verbal skills into a large language model to obtain a quality inspection result; the large language model can determine an integrity index score, a key point index score, a logicality index score and an emotion index score corresponding to a single sentence verbal skill in the customer service verbal skill based on a preset instruction and a target standard verbal skill so as to output a quality inspection result. According to the method, the integrity, the key points, the logicality and the emotional expression of the dialogue are deeply analyzed by utilizing a large language model, the method is not limited to literal matching any more, and higher flexibility and accuracy are realized in customer service dialogue quality inspection.
Owner:CHINA MOBILE ZHIJIE TECHNOLOGY (BEIJING) CO LTD +2

Real-time summarization of virtual conference transcripts

One example method includes receiving, during a virtual conference from a client device, a request to generate a real-time summary of the virtual conference, a plurality of client devices participating in the virtual conference and exchanging audio and video streams; receiving, during the virtual conference, a plurality of utterances generated by automatic speech recognition (“ASR”) of the audio streams; generating a group of consecutive utterances from the plurality of utterances; determining a segment based on the group of consecutive utterances; generating, using a large language model (“LLM”), a segment summary based on the segment; and providing the segment summary to the client device.
Owner:ZOOM COMMUNICATIONS INC

Utterance endpointing in task-oriented conversational systems

A task-oriented dialog system determines an endpoint in a user utterance by receiving incremental portions of a user utterance that is provided in real time during a task-oriented communication session between a user and a virtual agent (VA). The task-oriented dialog system recognizes words in the incremental portions using an automated speech recognition (ASR) model and generates semantic information for the incremental portions of the utterance by applying a natural language processing (NLP) model to the recognized words. An acoustic-prosodic signature of the incremental portions of the utterance is generated using an acoustic-prosodic model. The task-oriented dialog system can generate a feature vector that represents the incrementally recognized words, the semantic information, the acoustic-prosodic signature, and corresponding confidence scores of the model outputs. A model is applied to the feature vector to identify a likely endpoint in the user utterance.
Owner:INTERACTIONS LLC (US)

Detecting and using non-textual information in human speech

PCT designated stage expiredWO2025141559A1Speech recognitionMachine learningEncoder decoderAcoustic model
Automatic recognition of non-verbal messages in speech, and in particular to detection or analysis of prosodic multilayered analysis of intonation units such as prosodic unit prototypes and their multi-labeled variations, may form a hierarchical classification for the analysis of non¬ verbal information or cues in speech. A speech captured by a microphone is fed to a weakly- supervised deep learning acoustic model for speech recognition and transcription, that may be based on encoder-decoder Transformer architecture, such as Whisper by OpenAI. The model is trained to output multiple words form the text in the captured speech, to identify Intonation Units (IUs) that include one or more words, and associate non-verbal labels to each of the IUs. The labels may indicate a prototype, a discourse function (such as a conversation action), an emotion, an emphasis, or an attitude, as well as a genre of a part of, or whole of, the entire captured speech.
Owner:YEDA RES & DEV CO LTD

Control system

To enable appropriate response to an utterance of a user.SOLUTION: A control system disclosed herein comprises an input unit for receiving user input, a processing unit for performing specific processing using a sentence generation model for generating a sentence according to an input sentence, and an output unit configured to control an action of an electronic device to output a result of the specific processing. The processing unit determines whether or not the user input includes a travel itinerary creation request and, when affirmative, acquires user interest information to acquire a result of the specific processing using an output of the sentence generation model that uses a text instructing creation of a travel itinerary according to the interest information and information obtained from the user input as the input sentence.SELECTED DRAWING: Figure 2A
Owner:SOFTBANK GROUP CORP

Emotion understanding and feedback method for full-duplex interactive question and answer digital human

The invention discloses an emotional understanding and feedback method for a full-duplex interactive question-answering digital person, and the method comprises the steps: S1, arousing interaction: enabling a digital person of a digital person system to enter an interaction state in a human body detection arousing or voice instruction arousing manner by a user; s2, state analysis: the digital human system judges the state of the user in real time by collecting image data and audio data of the user, and identifies and analyzes the direction, emotion and speech content of the user in real time; and S3, feedback output: the digital human system drives the digital human in voice, expression and body movement through a screen in real time according to the analysis result of the direction, emotion and speech content of the user, and feeds back the result to the user in a manner of adding auxiliary characters, images and videos. The method has the advantages that the emotional state of the user is accurately judged through an advanced algorithm, digital human expressions, body actions and voice feedback are driven in real time according to the emotion and speech content of the user, response is made in time, and a real-person-like real-time interaction scene is achieved.
Owner:NEW ONE (BEIJING) TECH CO LTD

System and method for augmenting training data for natural language to meaning representation language systems

Techniques for augmenting training data include accessing training data comprising a plurality of training examples comprising a first training example comprising a first natural language utterance and a first logical form for the first natural language utterance. A second natural language utterance is generated by adding or replacing one or more values in the first natural language utterance. A logical form for the second natural language utterance is generated. A second training example is generated, comprising the second natural language utterance and the logical form for the second natural language utterance. The training data is augmented by adding the second training example to the plurality of training examples to generate an augmented training data set. A machine learning model is trained to generate logical forms for utterances using the augmented training data set.
Owner:ORACLE INT CORP

Logical text passage generation and retrieval for retrieval-augmented generation

Techniques for logical text passage generation and retrieval for retrieval-augmented generation. The techniques involve processing markup language documents to generate logical text passages and their corresponding embeddings. These embeddings are indexed for efficient retrieval. Upon receiving a user utterance, a user query is formed and transformed into an embedding to query the index. Relevant text passages are identified and used to prompt a large language model (LLM), which generates a completion. This completion is then sent as a response to the user. The process effectively bridges user queries with relevant information through advanced embedding and natural language processing techniques, enabling accurate and contextually appropriate interactions within a user-agent dialogue framework.
Owner:AMAZON TECH INC

Organization-specific cybersecurity dialogue system with large language models

An organization-specific cybersecurity dialogue system (“system”) intelligently generates responses to user utterances for cybersecurity by employing documentation and playbook agents for an associated cybersecurity organization. The system extracts an intent and an intent category from a user utterance, extracts relevant entities from the intent and uses them to determine relevant user telemetry data, and matches the intent, intent category, and user telemetry data to documents of the cybersecurity organization. The system then determines whether to generate a response based on matching document, matching playbook agents, or to prompt a user to create a ticket according to logic applied to the intent, intent category, user telemetry data, and matching documents and generates a corresponding response with large language models.
Owner:PALO ALTO NETWORKS INC

Techniques for transforming natural language conversation into a visualization representation

Techniques are disclosed herein for transforming natural language conversations into a visual output. In one aspect, a computer-implement method includes generating an input string by concatenating a natural language utterance with a schema representation comprising a set of entities for visualization actions, generating, by a first encoder of a machine learning model, one or more embeddings of the input string, encoding, by a second encoder of the machine learning model, relations between elements in the schema representation and words in the natural language utterance based on the one or more embeddings, generating, by a grammar-based decoder of the machine learning model and based on the encoded relations and the one or more embeddings, an intermediate logical form that represents at least the query, the one or more visualization actions, or the combination thereof, and generating, based on the intermediate logical form, a command for a computing system.
Owner:ORACLE INT CORP

Precise international communication digital human real-time dialogue method fused with multi-modal technology

The invention discloses an accurate international communication digital human real-time dialogue method fused with a multi-modal technology. The method comprises the following steps: S1, constructing a digital human image and tone; s2, propagation content generation and problem guidance; s3, semantic analysis and intention clarification based on the real-time voice dialogue; s4, geographic preference modeling and path planning; s5, cross-context propagation content generated based on retrieval enhancement is generated; s6, visually displaying the propagation content; and S7, carrying out digital human-driven multi-language propagation content real-time output and feedback closed-loop optimization. Through accurate utterance expression analysis, accurate international propagation problem recommendation is provided, cross-context propagation content generation based on semantic understanding is realized, digital people with voice features and visual images are constructed, real-time dialogue interaction of users is realized, and user experience is improved. The system can carry out geographic modeling according to the region where the accurate problem is located, language preference and propagation object culture characteristics, and differential propagation path planning is achieved.
Owner:HUNAN NORMAL UNIVERSITY

Systems and methods for training a neural network model using knowledge from pre-trained large language models

Embodiments described herein provide a training framework for generative NLP models that operate on previously learnt knowledge from pretrained large language models. Specifically, to train an NLP model to generate a response to a user utterance (e.g., “resolve login issue”), document embeddings of support IT documents encoded by a pretrained LLM are fed to an NLP decoder together with a training dialogue (e.g., a dialogue between the chat agent on how to “resolve login issue”). The NLP decoder can thus be trained by a causal language modeling loss computed based on the predicted next token and the ground-truth token from the training dialogue.
Owner:SALESFORCE INC

Using large language model(s) in generating automated assistant response(s)

As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.
Owner:GOOGLE LLC

Hybrid ai architecture for natural language query

Example solutions perform natural language query processing on hybrid utterances. A precise segment is identified, within the hybrid utterance, and processed with a symbolic AI interpreter configured to generate a first interpretation. The precise segment is replaced, within the hybrid utterance, with a placeholder term thereby resulting in a vague utterance. The vague utterance is processed with a statistical AI interpreter configured to generate a second interpretation. The first interpretation is merged with the second interpretation using the hybrid utterance as a template for the merger and using the placeholder term as the location for the first interpretation within the second interpretation. A complete interpretation is generated and transmitted to a query generator.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Reversible speech-to-speech translation for conversational ai systems and applications

PendingUS20240428020A1Natural language translationSemantic analysisSpeech to speech translationMedicine
Disclosed are apparatuses, systems, and techniques that may use machine learning for reversible translations of speech utterances. The techniques include training and using duplex neural networks (NNs) having a first subnetwork and a second subnetwork that are mirror images of each other. Training data for training the duplex NNs may include a target output that includes a first speech utterance in a first language, a first training input that includes the target output distorted by a noise, and a second training input that includes a second speech utterance in a second language. The duplex NNs may be trained to identify, using the first training input and the second training input, at least one of the target output or the first noise.
Owner:NVIDIA CORP

Detecting corrupted speech in voice-based computer interfaces

Approaches are generally described for corrupted speech detection in voice-based computer interfaces. First input data including first audio data representing a user utterance may be received. First data representing the first audio data may be generated using a first encoder. First text data representing a transcription of the user utterance may be generated. Second data representing the first text data may be generated using a second encoder different from the first encoder. Third data may be generated by combining the first data and the second data. The third data may be sent to a classifier network trained to predict a relevant corruption state for speech processing inputs. The classifier network may determine that the first input data corresponds to a first corruption state.
Owner:AMAZON TECH INC

Audio and video recording-based ASR identification enhancement method

The invention discloses an ASR identification enhancement method based on audio and video recording. According to the method, the accuracy and compliance of voice recognition in the financial service interaction process are improved by fusing the audio and environment feature information in the banking business double-recording scene. The method comprises the following steps: firstly, constructing an acoustic model for a bank outlet environment, and extracting audio features and interaction scene information of conversation between a client and a worker; and then, designing a vocabulary recognition module special for the financial field, dynamically adjusting language model parameters according to professional term libraries and utterance modes of different business types, and effectively coping with key links such as financial product introduction, risk prompt and customer confirmation. Compared with a traditional ASR system, the voice recognition accuracy in the banking business handling process is remarkably improved, particularly, key term recognition and important information extraction are prominent, and more reliable technical support is provided for financial service standardized management and double-recording quality inspection.
Owner:GUANGZHOU BAIRUI NETWORK TECH CO LTD

Deepfake detection

Disclosed are systems and methods including software processes executed by a server that detect audio-based synthetic speech (“deepfakes”) in a call conversation. The server applies an NLP engine to transcribe call audio and analyze the text for anomalous patterns to detect synthetic speech. Additionally or alternatively, the server executes a voice “liveness” detection system for detecting machine speech, such as synthetic speech or replayed speech. The system performs phrase repetition detection, background change detection, and passive voice liveness detection in call audio signals to detect liveness of a speech utterance. An automated model update module allows the liveness detection model to adapt to new types of presentation attacks, based on the human provided feedback.
Owner:PINDROP SECURITY INC

Intent discovery using large language models

Systems and methods to cause an intent discovery system to identify new user intents without additional training. The system may comprise of two neural networks. The first neural network generates a prompt tailored to a particular domain (e.g., travel), and may include known intents pertinent to the domain selected examples from a training dataset to provide context to the prompt. The second neural network may use this prompt to identify intents from new utterances in the prompt. The identified intents that are not in the list of known intents are then used to update the database.
Owner:SERVICENOW INC

System and method for contextual analysis and metadata database generation for user-specific speech patterns

A system for contextual analysis and metadata database generation for user-specific speech patterns is disclosed. The system accesses a speech signal of a user and identifies the user based on the voice print associated with the user. The system splits the speech signal into a first set of audio frames, where each audio frame comprises an utterance of one or more words. The system determines a context associated with each word. In response, the system detects a context change between a first text and a second text. The system generates a contextually split set of frames by splitting the speech signal into a second set of audio frames according to the detected context changes.
Owner:BANK OF AMERICA CORP

Model robustness on operators and triggering keywords in natural language to a meaning representation language system

ActiveUS20250156649A1Natural language translationRepresentation languageData set
Techniques are disclosed herein for improving model robustness on operators and triggering keywords in natural language to a meaning representation language system. The techniques include augmenting an original set of training data for a target robustness bucket by leveraging a combination of two training data generation techniques: (1) modification of existing training examples and (2) synthetic template-based example generation. The resulting set of augmented data examples from the two training data generation techniques are appended to the original set of training data to generate an augmented training data set and the augmented training data set is used to train a machine learning model to generate logical forms for utterances.
Owner:ORACLE INT CORP

Automated generation of targeted feedback using speech characteristics extracted from audio samples to address speech defects

Provided herein are systems and methods for providing instructions for speech based on speech classifications of verbal communications from users. Ae computing system can generate speech characteristics for a first verbal communication using a first audio sample from a user. The computing system can determine, from a plurality of speech classifications, a first speech classification for the first verbal communication based on the speech characteristics. The computing system can select, from a plurality of actions, an action comprising modifying one or more of the speech characteristics to define an utterance for the user based on the first speech classification. The computing system can provide an instruction presenting a message to prompt the user to perform the utterance defined by the action selected from the plurality of actions. The efficacy of the medication that the user is taking to address the condition may be increased.
Owner:CLICK THERAPEUTICS INC

Harassment information providing device, harassment information providing method and computer program

To provide technology that can present convincing information that leads to suppression of harassment to a person who has made a statement that raises concerns about harassment in a conversation.SOLUTION: A harassment information providing device is equipped with a transcription unit, a determination unit, and an output unit. The transcription unit converts speaker's remarks into text from voice data of conversation. The determination unit calculates a degree of negativity and positivity of the conversation by analyzing the text data representing the textualized statements, and determines a degree of harassment of the conversation using the negativity and positivity. The output unit outputs harassment information including information representing the degree of harassment.SELECTED DRAWING: Figure 11
Owner:NEC CORP

Low-resource task-oriented semantic parsing via intrinsic modeling for assistant systems

In one embodiment, a method includes receiving training utterances associated with a domain, receiving ontology labels for the domain, wherein the ontology labels comprise one or more of an intent or a slot, generating an inventory for the domain, wherein the inventory comprises at least a respective index and respective span for each intent or slot, wherein the respective span comprises a respective descriptive label associated with the intent or slot, and wherein the respective descriptive label comprises a natural-language description of the intent or slot, generating frames for training utterances based on the training utterances and the inventory by a natural-language understanding (NLU) model, wherein each frame comprises a structural representation of the respective training utterance, wherein the structural representation is generated based on a comparison between the corresponding training utterance and the inventory, and updating the NLU model based on the frames.
Owner:META PLATFORMS INC

Audio driven facial animation using machine learning

The invention discloses audio-driven facial animation using machine learning. Systems and methods of the present disclosure include animating an avatar or proxy according to input audio and one or more selected or determined emotions and / or styles. For example, a deep neural network may be trained to output motion or deformation information of a character representing that the character spokes an utterance contained in the audio input. The character may have different facial components or regions (e.g., head, skin, eyes, tongue) that are modeled individually, such that the network may output motion or deformation information for each of these different facial components. During training, the network may train associated decoders using weighted feature vectors using converter-based audio encoders with locked parameters. The network output may be provided to a renderer to generate a mood-accurate audio-driven facial animation.
Owner:NVIDIA CORP

Data augmentation for intent classification

The present disclosure relates to a data augmentation system and method that uses a large pre-trained encoder language model to generate new, useful intent samples from existing intent samples without fine-tuning. In certain embodiments, for a given class (intent), a limited number of sample utterances of a seed intent classification dataset may be concatenated and provided as input to the encoder language model, which may generate new sample utterances for the given class (intent). Additionally, when the augmented dataset is used to fine-tune an encoder language model of an intent classifier, this technique improves the performance of the intent classifier.
Owner:SERVICENOW INC