| Document |
Document Title |
|
WO/2024/019799A1 |
A method (700) for training a sub-model (215) for contextual biasing for speech recognition includes obtaining a base speech recognition model (200) trained on non-biased data (510). The method includes obtaining a set of training uttera...
|
|
WO/2024/018439A1 |
Object Provided are acoustic article s that take into account the frequency dependence of acoustic performance due to high bulk density and laminated structure. Solution Means The acoustic article s include a first member 2 in sheet form...
|
|
WO/2024/019878A1 |
A method (500) includes receiving training data that includes a set of unspoken textual utterances (320). For each respective unspoken textual utterance, the method includes, tokenizing the respective textual utterance into a sequence of...
|
|
WO/2024/019931A1 |
A method (400) includes processing, using a speech recognizer (200), a first portion of audio data (110) to generate a first lattice (210), and generating a first partial transcription (120) for an utterance (106) based on the first latt...
|
|
WO/2024/018598A1 |
An information processing system according to an embodiment of the present disclosure has: a selection unit which is configured to select a speech recognition dictionary to be used for speech recognition from among multiple speech recogn...
|
|
WO/2024/018429A1 |
An audio signal processing method, an audio signal processing apparatus, a computer device and a storage medium are provided. The audio signal processing method includes acquiring, by using the voice registration module based on a first ...
|
|
WO/2024/019199A1 |
The present invention relates to a business management system comprising: an interface through which information is input from a practitioner terminal or a customer terminal or output to the practitioner terminal or the customer terminal...
|
|
WO/2024/019817A1 |
Systems and methods for customized dialogue support in virtual environments are provided. Dialogue maps stored in memory may specify dialogue triggers each associated with a corresponding dialogue instruction. Data regarding an interacti...
|
|
WO/2024/017110A1 |
A voice noise reduction method, a model training method, an apparatus, a device, a medium, and a product. The voice noise reduction method comprises: using a preset voice activity detection algorithm to detect a current audio frame to be...
|
|
WO/2024/016793A1 |
A voice signal processing method and apparatus, a device, and a computer readable storage medium. The method comprises: determining first direction information of a target sound source according to an original voice signal acquired by a ...
|
|
WO/2024/018775A1 |
This pickup device 7 comprises: a bobbin 20 having two plates 21 that are disposed at a distance from each other in the plate thickness direction and that extend in a first direction orthogonal to the plate thickness direction, and a plu...
|
|
WO/2024/019277A1 |
A noise prevention resonator installation method according to an embodiment of the present invention may comprise: a sound absorption hole formation step of forming, in a ceiling or an inner wall, a plurality of sound absorption holes fo...
|
|
WO/2024/017800A1 |
A method for processing an input audio signal, comprising conditioning a first neural network system with a representation of the input audio signal to predict a bit-rate reduced representation of a processed input audio signal, the firs...
|
|
WO/2024/019802A1 |
Methods, systems, and apparatus for normalizing audio transmissions from multiple endpoints within a teleconference. A first audio transmission from a first participant of a teleconference can be received for presentation at the teleconf...
|
|
WO/2024/019660A1 |
A sound absorption material and a method (10) of fabricating a sound absorption material are provided. The method (10) includes preparing (12) a first precursor solution or suspension of one of a first triboelectric material and a second...
|
|
WO/2024/020196A1 |
This disclosure relates generally to electronic musical instruments, systems, and methods. More particularly, this disclosure relates to electronic percussion instruments such as tom toms, snare drums, bass drums, cymbals, and hi-hats, a...
|
|
WO/2023/246151A9 |
A display device and a control method, being applied to the technical field of display. The display device (200) comprises: a controller (250), configured to receive a target control request of a user for the display device (S710), in re...
|
|
WO/2024/018518A1 |
The present invention provides a model training device including an utterance feature reconfiguration model training unit that performs masking by randomly selecting a portion of an utterance feature sequence, which is a sequence of utte...
|
|
WO/2024/013083A1 |
The present invention relates to a method for preparing porous adsorbent particles. The present invention also relates to a porous adsorbent particle and a sampling device containing a plurality of said particles. The present invention a...
|
|
WO/2024/013469A1 |
A method (100) of designing a segmented display device (1) having a plurality of elements (5) arranged in an array (3), each element (5) providing an individual output such that the plurality of elements (5) form a collective output of t...
|
|
WO/2024/012284A1 |
Provided in the embodiments of the present disclosure are an audio recognition method and apparatus, and an electronic device and a computer program product. The method may comprise acquiring a target feature map of audio data on the bas...
|
|
WO/2024/015840A1 |
Systems and methods for generating real-time directional haptic output that is capable of being perceived by a user. A system is described that includes a haptic computing device configured to receive an audio input and provide real-time...
|
|
WO/2024/013662A1 |
The present invention relates to a sound-absorbing device (1) comprising: - a first and second wall (2, 3) spaced along a thickness direction (Z-Z), delimiting the device (1) on opposite sides, and having a respective reference plane (C)...
|
|
WO/2024/011964A1 |
A silencer (100), comprising: a waveguide tube (10), a sound absorption tube (20) and a reflection tube (30), the waveguide tube (10) being provided with a sound wave inlet. The sound absorption tube (20) and the reflection tube (30) are...
|
|
WO/2024/013099A1 |
A method includes receiving audio stream data associated with a data capture environment, and receiving sensor data associated with the data capture environment. The method also includes identifying at least some events in the sensor dat...
|
|
WO/2024/012805A1 |
An apparatus, for generating spatial audio signals, the apparatus comprising means configured to: obtain at least two audio signals; obtain at least one metadata directional parameter associated with the at least two audio signals; gener...
|
|
WO/2024/014819A1 |
Multimodal disentanglement can include generating a set of silhouette images corresponding to a human face, the generating undoing a correlation between an upper portion and a lower portion of the human face depicted by each silhouette i...
|
|
WO/2024/015782A1 |
Systems and methods are provided for performing automated speech recognition. The systems and methods perform operations comprising: accessing a language model that includes a plurality of n-grams, each of the plurality of n-grams compri...
|
|
WO/2024/012040A1 |
A method for speech generation and a related device, the method includes: obtaining a first source data input to a speech generation model (100) including multiple encoders(111,112) and a decoder(120)(701), where types of input data of t...
|
|
WO/2024/015283A1 |
A method (400) includes receiving follow-on audio data (127) captured by an assistant-enabled device (102), the follow-on audio data corresponding to a follow-on query (129) spoken to a digital assistant (109) subsequent to a user submit...
|
|
WO/2024/014324A1 |
A speech recognition device 100 according to the present disclosure comprises a conversion unit 121 for converting speech by a speaker into a feature vector, a weighting unit 122 for weighting the feature vector by the degree of importan...
|
|
WO/2024/012501A1 |
Disclosed in the present application are a speech processing method and a related apparatus, an electronic device, and a storage medium. The speech processing method comprises: acquiring a speech duration of blank speech, which persists ...
|
|
WO/2024/014625A1 |
The present invention provides a personalized fragrance recommendation service providing system and method therefor. The personalized fragrance recommendation service providing method, performed by a server, may comprise the steps of: re...
|
|
WO/2024/012794A1 |
The present disclosure relates to a device and a computer-implemented method for voice control of a motor vehicle, and to a corresponding motor vehicle. The device (1100) has an interface (1110) which is designed to communicate informati...
|
|
WO/2024/014492A1 |
A musical composition distribution system 1 comprises a plurality of terminal devices 10 that are respectively used by a plurality of users, and a server 20 that is capable of communicating with the plurality of terminal devices 10, wher...
|
|
WO/2024/014870A1 |
Embodiments herein provide a method and electronic device (100) for interactive image segmentation. The method includes receiving one or more user inputs for segmenting at least one object from among a plurality of objects in an image. T...
|
|
WO/2024/012665A1 |
An apparatus (300) for generating one or more audio output signals from one or more encoded audio signals according to an embodiment is provided. The apparatus (300) comprises an input interface (310) for receiving the one or more encode...
|
|
WO/2024/014824A1 |
Disclosed are a pet robot apparatus based on identity authentication using voice recognition and a method for operating same. A pet robot apparatus according to an embodiment can be controlled according to a behavior pattern correspondin...
|
|
WO/2024/015456A1 |
A speaking device may be fitted to a user's mouth or mouth and nose and sealed against the user's face in order to provide a sealed airspace for oral communications while underwater. The speaking device is collapsible while not in use an...
|
|
WO/2024/012666A1 |
An apparatus (100) for generating one or more audio output signals from one or more encoded audio signals according to an embodiment is provided. The apparatus (100) comprises at least one entropy decoding module (110) for decoding encod...
|
|
WO/2024/015140A1 |
A method (500) includes obtaining a corpus of unlabeled training data (358) that includes a plurality of spoken utterances (360), each corresponding spoken utterance of the plurality of spoken utterances includes audio data (362) charact...
|
|
WO/2024/013085A1 |
A method data augmentation includes receiving audio stream data associated with at least one impulse event, receiving a label associated with the audio stream data, and detecting, using an onset detector, at least one peak of the at leas...
|
|
WO/2024/015130A1 |
A ring assembly of an underwater acoustic sensor (hydrophone) system includes a ring that has brackets that mount the hydrophones evenly circumferentially spaced apart. The ring assembly may have three hydrophones mounted on the ring, wi...
|
|
WO/2024/013266A1 |
An apparatus (100) for generating one or more audio output signals from one or more encoded audio signals according to an embodiment is provided. The apparatus (100) comprises at least one entropy decoding module (110) for decoding encod...
|
|
WO/2024/012257A1 |
An audio processing method and apparatus (170), and an electronic device (1800). The method comprises: displaying a first page (S401), wherein the first page comprises a first chord of first audio; in response to a trigger operation perf...
|
|
WO/2024/012113A1 |
Disclosed in the present application is a smart photographic system of a vehicle. The smart photographic system of a vehicle comprises: a controller and a photographic apparatus, which is in wireless connection with the controller. The c...
|
|
WO/2024/011902A1 |
A speech recognition model training method and apparatus, a storage medium, and an electronic device. The speech recognition model training method comprises: constructing an initial speech recognition model (S101); fixing a second initia...
|
|
WO/2024/015352A1 |
Provided for are systems and methods for real-time translation between a user and one or more participants in the conversation, the user and one or more participants speaking different languages. The user is equipped with a communication...
|
|
WO/2024/014869A1 |
An embodiment of the present disclosure may comprise at least one microphone, at least one speaker, a communication module, a display, a memory, and a processor operatively connected to at least one of the at least one microphone, the at...
|
|
WO/2024/014318A1 |
This learning model generation device has: a voice training data generation unit for generating training voice data by incorporating silent-period special voice data in a silent period of input voice data of a speaker; and a motion infor...
|
