| Document |
Document Title |
|
WO/2023/209632A1 |
There is provided a computer-implemented method of training a speech-to-speech (S2S) machine learning (ML) model for adapting voice attribute(s) of speech, comprising: creating an S2S training dataset of S2S records, wherein an S2S recor...
|
|
WO/2023/211128A1 |
The present invention relates to an AI-based disease diagnosis method using voice data, the method comprises the steps of: collecting first voice data; removing at least one of noise, unique characteristics of a voice, and disease charac...
|
|
WO/2023/209993A1 |
A signal processing device (10) has: an instantaneous spatial covariance matrix (ISCM) calculation unit (11) for estimating a time frequency mask for an observation signal and calculating, for all observation times for an observation sig...
|
|
WO/2023/207575A1 |
The present utility model relates to the technical field of instrument stands, and discloses an electronic drum stand, comprising a U-shaped frame and two bases; the frame comprises a horizontal tube that is horizontally arranged and two...
|
|
WO/2023/206327A1 |
Solutions for custom display post processing (DPP) in speech recognition (SR) use a customized multi-stage DPP pipeline that transforms a stream of SR tokens from lexical form to display form. A first transformation stage of the DPP pipe...
|
|
WO/2023/210978A1 |
In an embodiment, an audio processing method comprises the steps of: parsing a bitstream so as to obtain at least one substream and additional information; decompressing the at least one substream so as to obtain at least one audio signa...
|
|
WO/2023/206928A1 |
A speech processing method and apparatus, a device, and a computer-readable storage medium. The method comprises: pre-constructing a speech synthesis model and a parallel speech conversion model, synthesizing a target text into an interm...
|
|
WO/2023/208402A1 |
The invention relates to a noise suppression device for a motor vehicle, having: (i) a number of acceleration sensors for detecting vibrations which may be generated by wheels of the motor vehicle which move on a road surface, and as a r...
|
|
WO/2023/206714A1 |
Provided in the present invention is a loudspeaker. The loudspeaker comprises a cavity filled with a sound absorption material, wherein the cavity is further filled with expandable foam which expands after being triggered, so as to limit...
|
|
WO/2023/211654A1 |
An example method includes hosting, by a conference provider, a virtual conference between a plurality of client devices exchanging audio streams; receiving, during the virtual conference, a first plurality of audio segments of a first a...
|
|
WO/2023/208792A1 |
The invention relates to a method (28) for operating an electromotive adjustment drive (16) of a motor vehicle (2), having an electric motor (18) and an adjustment part (20) driven thereby. In a feedback mode (34), the electric motor (18...
|
|
WO/2023/212073A1 |
A sound management system for a virtual production volume may include one or more acoustic baffles configured to reduce sound reverberation within the production volume while allowing transmission of visible light through the baffle. In ...
|
|
WO/2023/205832A1 |
The invention relates to a method (30) and a system (20) for evaluating an electric motor (12) of an electric drive system (11) of a motor vehicle (10) with respect to the audible and/or perceptible vibrations thereof during operation.
|
|
WO/2023/211554A1 |
Systems generate segments of spoken language utterances based on different sets of segmentation boundaries. The systems are also configured to generate one or more formatted segments by assigning a punctuation tags at segmentation bounda...
|
|
WO/2023/206907A1 |
An information display method and apparatus, a computer readable storage medium, and an electronic device, relating to the technical field of human-computer interaction. The method comprises: displaying an interactive interface in a firs...
|
|
WO/2023/209337A1 |
There is provided an acoustic black hole comprising: in a first axis, along a line, a variation from a first characteristic to a second characteristic to a third characteristic, wherein the acoustic black hole comprises a taper from the ...
|
|
WO/2023/206686A1 |
A control method for a smart device, and a storage medium and an electronic apparatus, which relate to the field of home automation/smart homes. The method comprises: acquiring a first sound signal received by a first device and a second...
|
|
WO/2023/212271A1 |
Systems and methods for observation-based training of an Artificial Intelligence (Al) character model are provided. An example method includes receiving log data including interactions of a first user and a second user and adjusting, bas...
|
|
WO/2023/209339A1 |
There is provided an acoustic black hole comprising: in a first axis, a variation from a first characteristic to a second characteristic, along a line; in a second axis different to the first axis, a variation from a first characteristic...
|
|
WO/2023/211865A1 |
Systems and methods of using machine learning for identifying glass breakage events can include (a) accessing or obtaining the machine learning mode, (b) obtaining audio data, (c) determining, by processing the audio data using the machi...
|
|
WO/2023/207212A1 |
A voice dialogue detection method and apparatus. The voice dialogue detection method comprises : on the basis of dialogue-related information and dialogue text of a plurality of dialogue sentences in target voice data, performing interru...
|
|
WO/2023/207472A1 |
An audio synthesis method, a device and a computer-readable storage medium. The method comprises: acquiring song audio to be processed and corresponding song information (S101); performing human voice separation processing on the song au...
|
|
WO/2023/211774A1 |
A method for facilitating automated participant record augmentation via a secured repository is disclosed. The method includes aggregating, via an application programming interface, employee data from sources according to a predetermined...
|
|
WO/2023/212442A1 |
A device includes a neural network, a first subband neural network, a second subband neural network, and a reconstructor. The neural network processes neural network inputs to generate a neural network output. The neural network inputs i...
|
|
WO/2023/207149A1 |
A speech recognition method and an electronic device. The method can be applied to a terminal device, such as a mobile phone or a tablet computer. The terminal device may receive a user-defined wake-up word that is set by a user, and the...
|
|
WO/2023/209274A1 |
According to an embodiment, a computer- implemented method for punctuation of text from an audio comprises: obtaining an audio input comprising speech data; identifying a plurality of silent sections in the audio input; grouping the plur...
|
|
WO/2023/207541A1 |
A speech processing method and a related device, which are applied to the field of song editing. The method comprises: acquiring original speech and second text; predicting a second pitch feature of the second text according to a first p...
|
|
WO/2023/209283A1 |
The invention relates to a pick (1) for a guitar, the pick comprising a clamping part (2) that has a hole (4) passing all the way through it, and a gripping element (3) having: - a body (5) having a cross-sectional area that is 1 to 10% ...
|
|
WO/2023/210375A1 |
This stringed instrument comprises a musical instrument body 2, strings, a saddle 5 inserted into a groove 9 formed in the musical instrument body 2 to support the strings, and a pickup 6 that has a porous layer stretchable and deformabl...
|
|
WO/2023/208342A1 |
An apparatus for generating one or more audio output channels from one or more audio signals is provided. The apparatus comprises a gain determiner (110) configured to generate or to receive gain information, wherein the gain information...
|
|
WO/2023/211671A1 |
One example method includes receiving, by a virtual conference provider, a list of words associated with an entity or a context; establishing, by the virtual conference provider, a virtual conference; joining, by the virtual conference p...
|
|
WO/2023/208641A1 |
The invention relates to a method (30) for operating a noise reduction unit (16) of a motor vehicle (2), which has a noise output means (18) and an active noise cancelling unit (22). By means of the active noise cancelling unit (22), an ...
|
|
WO/2023/210340A1 |
A learning device (100) according to one embodiment of the present disclosure comprises an acquisition unit (131) that acquires content of a command input by a user to a predetermined information processing system, and a learning unit (1...
|
|
WO/2023/207193A1 |
An audio separation method and apparatus, a training method and apparatus, and a device, a storage medium and a product, which relate to the field of artificial intelligence. The audio separation method comprises: acquiring an (i-1)th au...
|
|
WO/2023/211443A1 |
An electronic device obtains input audio data having a plurality of audio sentences in a temporal domain and converts the input audio data to a plurality of audio frequency components in a. spectral domain. Each audio sentence includes a...
|
|
WO/2023/212690A1 |
Various embodiments of the present disclosure provide methods, apparatus, systems, devices, and/or the like for reducing defects of audio signal samples by using at least one of audio source feature separation machine learning models, au...
|
|
WO/2023/209338A1 |
There is provided an acoustic black hole comprising: in a first axis, a taper from a first thickness to a second thickness, along a line; in a second axis perpendicular to the first axis, and away from the line, one or more regions of di...
|
|
WO/2023/210149A1 |
Provided is an information processing device that carries out a process related to speech input.　This information processing device comprises: a classification unit for classifying uttered speech as normal speech or whispered speech on...
|
|
WO/2023/210914A1 |
The present techniques generally relate to a system and method for knowledge distillation between machine learning, ML, models. In particular, the present application relates to a computer-implemented method for training a condenser mode...
|
|
WO/2023/209898A1 |
A voice analysis device 1 according to an embodiment of the present invention has a voice acquisition unit 122 for acquiring a voice collected by a plurality of sound collecting devices arranged in a prescribed region, an identifying uni...
|
|
WO/2023/212441A1 |
A method includes performing, at a first neural network, a first decomposition operation on a transformed input speech signal to generate a voiced component of the transformed input speech signal. The transformed input speech signal incl...
|
|
WO/2023/210052A1 |
A voice analysis device 1 according to an embodiment of the present invention has: a voice acquisition unit 122 for acquiring the arrival direction of a voice for each of a plurality of sound collecting devices arranged in a prescribed r...
|
|
WO/2023/209598A1 |
Presented herein are techniques for dynamically generating test materials for implementing speech test to, for example, hearing aid users or users of cochlear implants. Dynamic word list generation techniques are disclosed. Such techniqu...
|
|
WO/2023/205437A1 |
The present invention relates to vortex ultrasound transducers and methods of therapeutic ultrasound treatment. A device for therapeutic ultrasound treatment includes a jacket for insertion within a blood vessel of a patient and an ultra...
|
|
WO/2023/202442A1 |
Embodiments of the present application relate to the technical field of terminals, and provide a method for waking up a device, an electronic device, and a storage medium. The method for waking up a device comprises: when it is determine...
|
|
WO/2023/204470A1 |
Provided are an artificial intelligence device and an automatic speaker recognition method therefor, which are capable of automatically recognizing a speaker on the basis of adaptive self learning using an active query, the device compri...
|
|
WO/2023/204837A1 |
A method for disentangled variational speech representation learning for voice conversion, performed by at least one processor, is provided. The method includes receiving input speech segments, encoding the input speech segments via a sh...
|
|
WO/2023/201886A1 |
A sound signal processing method and apparatus, an audio device, and a storage medium. The sound signal processing method comprises the following steps: determining a current array state of a microphone array, wherein the current array s...
|
|
WO/2023/204448A1 |
The present invention relates to a smart guest reception service system for responding to an order or service request of a customer by using an artificial intelligence speaker, and there are effects of instantaneously and accurately tran...
|
|
WO/2023/201810A1 |
A core-shell structure molecular sieve, taking a ZSM-5 molecular sieve with a mesoporous structure as a core phase, the silicon-aluminum mass ratio of silicon to aluminum of the core phase being 50-150. The core-shell structure molecular...
|
