| Document |
Document Title |
|
WO/2023/164380A1 |
A method (800) for training a memorized neural network (300) includes receiving a training input audio sequence (400) including a sequence of input frames defining a hotword that initiates a wake-up process on a user device (102). The me...
|
|
WO/2023/164332A1 |
There is provided a method that includes (a) obtaining a first voice vector that was derived from a signal of a voice that was sampled at a first sampling frequency, (b) obtaining a second voice vector that was derived from a signal of a...
|
|
WO/2023/162114A1 |
A training device (10) acquires utterance data of a speaker and information on the speaker, conversation data of a listener and information on the listener, and emotion information relating to the listener. The training device (10) then ...
|
|
WO/2023/163314A1 |
A method, performed in a metaverse system, for providing an evolvable avatar according to various embodiments of the present disclosure may comprise the steps of: creating a basic avatar used in a metaverse virtual space; collecting at l...
|
|
WO/2023/160447A1 |
A tuning device (100), comprising an adjusting assembly (10), an adjusting rod (20), and a connecting member (30). The adjusting assembly (10) comprises a housing (11), a transmission rod (12), and a transmission wheel (13) engaged with ...
|
|
WO/2023/160713A1 |
Music generation methods and apparatuses (1100, 1200), a device, a storage medium, and a program. A method comprises: determining a music template, the music template comprising a plurality of tracks, and each track being divided into at...
|
|
WO/2023/163270A1 |
An electronic device according to various embodiments disclosed in the present document comprises a processor and memory operatively connected to the processor. The memory can store instructions which, when executed, cause the processor ...
|
|
WO/2023/162581A1 |
This sound production device (100) comprises: an acquisition unit (131) that acquires spatial information indicating a region of a three-dimensional virtual space including a sound source object and one or more three-dimensional objects ...
|
|
WO/2023/161778A1 |
Low frequency acoustic room and environment. An inner wall portion (120) comprising a plurality of porous-but-resistive membranes (125) operatively configured along the wall portions (130) of the inner wall portion (120) wherein the poro...
|
|
WO/2023/163896A1 |
Systems and techniques are provided for processing audio data. For instance, a process can include obtaining a primary audio signal from a user computing device and obtaining first audio data from an additional computing device, wherein ...
|
|
WO/2023/157650A1 |
The present technology relates to a signal processing device and a signal processing method which can make it possible to preferably synthesize a plurality of pieces of encoded data. The signal processing device of the present technology...
|
|
WO/2023/156176A1 |
An apparatus comprising means for: obtaining a bitstream comprising encoded spatial metadata and encoded transport audio signals; decoding transport audio signals from the bitstream encoded transport audio signals; decoding spatial metad...
|
|
WO/2023/158784A1 |
A multi-mode hearing stimulation method for stimulating the perception of hearing in a subject. The method includes generating, based on sound signals representative of multi-channel sound, two or more of multi-channel electrical stimula...
|
|
WO/2023/158226A1 |
A speech synthesis method using an adversarial training technique according to an embodiment may comprise the steps of: receiving speech data input; training an adversarial model for speech synthesis on the basis of the speech data input...
|
|
WO/2023/157207A1 |
This signal analysis system comprises: an acquisition unit that acquires a conversion network that is learned using a first mel spectrogram sequence in a machine learning technique for acoustic conversion based on a discriminator-equippe...
|
|
WO/2023/156841A1 |
The present invention relates to a chromatic bass musical instrument, whose format is non-cumbersome and portable, played with the feet diagonally: from left to right and vice-versa, from top to bottom and vice-versa; which musical instr...
|
|
WO/2023/158282A1 |
An electronic apparatus is disclosed. The electronic apparatus comprises a dust collection filter, a voltage supply unit for applying a voltage to the dust collection filter, a microphone disposed within a critical distance from the dust...
|
|
WO/2023/157066A1 |
A computer executes a first learning procedure to learn a second model by updating a first model, to which a speaker vector representing a speaker, text, and a first acoustic feature related to speech obtained by the speaker uttering the...
|
|
WO/2023/158553A1 |
An automated speech recognition (ASR) transcript of at least a portion of a media content is obtained from an ASR tool. Suggested words are received for corrected words of the ASR transcript of the media content. Features are obtained us...
|
|
WO/2023/157186A1 |
An information processing device according to an embodiment of the present invention comprises a first acquiring unit and a recommendation information output unit. The first acquiring unit acquires configuration information relating to a...
|
|
WO/2023/155572A1 |
The present application provides an audio recognition method and an audio recognition device, which can improve the accuracy of acoustic event detection. The method comprises: acquiring an audio signal to be tested; determining, accordin...
|
|
WO/2023/158563A1 |
A method (300) includes receiving a current spectrogram frame (222) and reconstructing a phase of the current spectrogram frame by, for each corresponding committed spectrogram frame in a sequence of M number of committed spectrogram fra...
|
|
WO/2023/158076A1 |
Disclosed are an electronic device and an utterance processing method thereof. The electronic device according to various embodiments comprises: a microphone for receiving a first utterance of a user and a second utterance of the user ge...
|
|
WO/2023/156578A1 |
The present invention relates to the field of digital processing in order to reproduce the auditory impression of a "vinyl sound". Vinyl records were created in 1948; the sound information was reproduced by the movement of a needle trans...
|
|
WO/2023/157379A1 |
The present invention is a noise reduction system 1 for a railway vehicle for reducing, at a plurality of silencing positions 10 in a railway vehicle 100, noise propagated from a noise source in the exterior of the railway vehicle 100, t...
|
|
WO/2023/158468A1 |
A system and method and for monitoring an online meeting includes receiving an indication that the online meeting has been started, retrieving meeting metadata associated with the online meeting, meeting content data from the online meet...
|
|
WO/2023/158050A1 |
A method for providing an interaction with a virtual assistant, includes identifying, by an electronic device, at least one of a duration of a silence between a first portion of an utterance received from a user and a second portion of t...
|
|
WO/2023/157845A1 |
Provided are an acoustic signal processing method, an electronic apparatus, and a computer-readable recording medium having a program recorded thereon, all of which enable listening to properly processed sound on various devices. When mo...
|
|
WO/2023/158972A1 |
A method (400) includes obtaining a speaker identification (SID) model (151) trained to predict speaker embeddings (155) from utterances spoken by different speakers, the SID model includes a trained audio encoder (150) and a trained SID...
|
|
WO/2023/157159A1 |
Provided is technology for estimating the phase difference spectrum for signals of two channels by using a process suitable for fixed-point arithmetic, at a computational processing amount smaller than in the past. The present invention ...
|
|
WO/2023/157848A1 |
This active noise control system (500) comprises a structure (80), a first piezoelectric speaker (10A), and a second piezoelectric speaker (10B). The structure (80) has a front surface (80a) and a rear surface (80b). The first piezoelect...
|
|
WO/2023/155607A1 |
Terminal devices and voice wake-up methods, relating to the technical field of voice interaction. A first terminal device comprises: a first communication module used for receiving a voice signal to be recognized sent by a second termina...
|
|
WO/2023/158658A1 |
A system and method provide audio processing for on-line communications, including the elimination of unwanted and disruptive noises, enhancing the clarity of the participants voices, and further processing to establish an immersive 3D s...
|
|
WO/2023/156862A1 |
The invention concerns a gong (100) for a clock strike device. The gong (100) comprises a multilayer main body (10), which includes a central layer (13) made of metallic material and an upper layer (14) and a lower layer (15) made of pie...
|
|
WO/2023/157728A1 |
This sound design system comprises: a calculation unit configured to calculate a physical quantity of a sound of interest transmitted from a user whose auditory impression is desired to be identified; and an identification unit that comp...
|
|
WO/2023/157783A1 |
Provided is an information processing device which controls sound volume so that a user can reliably discern speech such as speech guidance without incompatibility in terms of the sense of hearing.　The information processing device com...
|
|
WO/2023/158460A1 |
Implementations relate to an application that can bias automatic speech recognition for meetings using data that may be associated with the meeting and/or meeting participants. A transcription of inputs provided during a meeting can addi...
|
|
WO/2023/157963A1 |
An information processing apparatus according to one aspect of the present disclosure is provided with: a means for acquiring information indicating the direction of a speech source with respect to at least one multi-microphone device; a...
|
|
WO/2023/155713A1 |
Disclosed in the embodiments of the present disclosure are a method and apparatus for marking a speaker, and an electronic device. A specific embodiment of the method comprises: acquiring a sound data frame sequence, and acquiring sound ...
|
|
WO/2023/158268A1 |
An electronic device according to various embodiments may comprise a sensor, microphones, and a processor, wherein the processor is configured to: acquire a first sound signal through at least some microphones among the microphones; acqu...
|
|
WO/2023/156786A1 |
A method for acoustic control of particles in a space, the method including: providing particles in the space, wherein the particles are in an initial state; selecting a desired state of the particles in the space to be achieved through ...
|
|
WO/2023/152803A1 |
A voice recognition device according to the present disclosure performs voice recognition on a voice signal inputted on manufacturing premises and uses the result as a voice command, the voice recognition device comprising: an adjustment...
|
|
WO/2023/150919A1 |
Disclosed in embodiments of the present description are an active noise reduction audio device, a method, and a storage medium. The device comprises: a loudspeaker, a microphone, an analog filter, and a processing circuit. The loudspeake...
|
|
WO/2023/154727A1 |
In one aspect, an audio playback device having at least one microphone captures a voice input. The playback device detects, within the voice input, at least one keyword from among a plurality of command keywords supported by the playback...
|
|
WO/2023/153033A1 |
An information processing device 10 generates, on the basis of score data SD representing a score including at least one performance mark, an acoustic signal representing a sound relating to the performance mark.
|
|
WO/2023/153314A1 |
In a situation where a driver is driving, if an HCU receives an operation for displaying a screen set to be subject to operation restrictions, the HCU displays the screen which is subject to restrictions in a form in which buttons subjec...
|
|
WO/2023/154527A1 |
Provided are systems, methods, and machine learning models for filling in gaps (e.g., of up to one second) in speech samples by leveraging an auxiliary textual input. Example machine learning models described herein can perform speech in...
|
|
WO/2023/152895A1 |
This waveform signal generation system comprises: a neural network function unit for, by changing through use of a neural network function a time component or a feature amount component of an intermediate representation signal representi...
|
|
WO/2023/154360A1 |
A method of correcting an automatic speech recognition (ASR) output of an ASR module, includes: providing a corrector model configured to receive the ASR output; pre-training and training the corrector model to map the ASR output to desi...
|
|
WO/2023/153555A1 |
An apparatus and a method for generating a speech synthesis image are disclosed. An apparatus for generating a speech synthesis image according to an embodiment relates to an apparatus for generating a speech synthesis image on the basis...
|
