Login| Sign Up| Help| Contact|

Patent Searching and Data


Matches 101 - 150 out of 213,998

Document Document Title
WO/2018/155480A1
An information processing device that comprises: an analysis processing unit that, in accordance with a feature value for the sound in content that includes video and sound, specifies a scene type for the content; and a setting processin...  
WO/2018/153200A1
A highway long short time memory (HLSTM) model-based acoustic modeling method and device, and a storage medium, the method comprising: training a randomly initialized HLSTM model on the basis of a preset function and optimizing a trainin...  
WO/2018/155807A1
Disclosed are an artificial intelligence (AI) system using a machine learning algorithm such as deep learning, and an application thereof. In particular, provided are an electronic device, a document display method therefor, and a non-tr...  
WO/2018/156334A1
Bending mode transducers are provided including a substrate made of a high density material, the substrate having a first surface and a second surface, opposite the first surface. A piezoelectric layer is provided on the first surface of...  
WO/2018/155936A1
Embodiments of the present disclosure relate to vision-based object recognition devices and methods for controlling the same. According to an embodiment of the present disclosure, an electronic device may comprise a camera, at least one ...  
WO/2018/154188A1
The invention relates to processing implemented by computer means of sound data output by at least one sensor and activation of at least one actuator of an acoustically radiating structure. The sensor (CAP) senses an acoustic signal outp...  
WO/2018/153243A1
The present application provides a masking method and device for motor high-frequency noises. The method comprises: generating a masking curvilinear function on the basis of a high-frequency noise signal generated by a motor; collecting,...  
WO/2018/155774A1
A system for specifying a target item corresponding to input information on the basis of the input information input to a terminal and a method therefor are disclosed. The system comprises: a first device; a second device; and a server s...  
WO/2018/154228A1
The invention relates to a percussive bell intended to be attached to a support member, in particular the handlebar of a bicycle, said bell comprising a bell element (1) and a hammer (2) which are mounted on a base (4) provided with a cl...  
WO/2018/153223A1
A speech conversion method comprising: acquiring a target text (S302); synthesizing a first machine speech corresponding to the target text (S304); from an asynchronous machine speech database, filtering out an asynchronous machine speec...  
WO/2018/156345A1
Ultrasonic devices include a transducer having a piezoelectric element therein that may operate as an acoustic signal receiving surface and/or an acoustic signal generating surface. At least one acoustic matching layer is provided on the...  
WO/2018/154175A1
Apparatus comprising one or more processors configured to: receive at least two microphone audio signals (101) for audio signal processing wherein the audio signal processing comprises at least a spatial audio signal processing (303) and...  
WO/2018/156248A1
An encoding for data in an audio data stream may be indicated in the data stream using a footer stored in low-order bits of data frames in the audio data stream. When the audio data stream may include either Pulse Code Modulation (PCM) o...  
WO/2018/155481A1
An information processing device that comprises a learning-data generation unit and an identification-model generation unit. The learning-data generation unit: sets, in accordance with instructions from a user, scene types for any of a p...  
WO/2018/155981A1
An aspect of the present invention provides a method for providing a voice recognition trigger, the method comprising the steps of: estimating a first distance, which is the distance between a device and a user, on the basis of proximity...  
WO/2018/154372A1
A computer-implemented method and an apparatus are provided. The method includes obtaining, by a processor, a frequency spectrum of an audio signal data. The method further includes extracting, by the processor, periodic indications from...  
WO/2018/154864A1
Provided is a thin, lightweight sound-absorbing material that has excellent low-frequency sound absorption. This sound-absorbing material has a laminate structure that includes, in order, a first perforated layer, a first porous layer, a...  
WO/2018/153213A1
A multi-language hybrid speech recognition method, which relates to the technical field of speech recognition. The method comprises: step S1, configuring a multi-language hybrid dictionary comprising multiple different languages; step S2...  
WO/2018/155116A1
[Problem] To provide an information processing device capable of definitively transmitting a message to a third party to whom a user wishes to transmit a message. [Solution] To provide an information processing device equipped with an ac...  
WO/2018/154434A1
Multi-step method for producing a composite component for vehicles and product thus obtained, in order to produce a cover made of thermoplastic material (200) and insulating foam (300); said method making use of a multiple mold (100) mad...  
WO/2018/154458A1
A system generates a holographic image of the celebrity who is also performing the song right next to the karaoke singer. The system enables remote/local audiences to perceive that the karaoke singer is performing a song next to and with...  
WO/2018/155800A1
Provided are a mobile device, a method for operating the same, and a non-transitory computer readable storage medium. The mobile device includes a touch display configured to sense a user input; a memory; and a processor configured to ex...  
WO/2018/154865A1
Provided is a thin, lightweight sound-absorbing material that has excellent low-frequency sound absorption. This sound-absorbing material has a laminate structure that includes a perforated layer and a porous layer. The sound-absorbing m...  
WO/2018/155026A1
An information processing device according to an embodiment of the present technology includes a user information acquisition unit, an object information acquisition unit, and an output control unit. The user information acquisition unit...  
WO/2018/153214A1
A training method and a speech recognition method for a hybrid frequency acoustic recognition model, which relate to the technical field of speech recognition. The method comprises: obtaining a first-type speech feature of a first speech...  
WO/2018/154996A1
This master reproduction device is capable of reproducing audio data synchronously with one or more slave reproduction devices. The master reproduction device is provided with a plurality of light emission elements, a generation unit, a ...  
WO/2018/155231A1
Provided are a sound source detecting method and detecting device which enable accurate detection of the position of a sound source using an acoustic intensity measurement result. In this detecting method, Iall, which is the total value ...  
WO/2018/153318A1
Disclosed is a noise-reducing device (92) used for a cabinet (91), the device comprising at least one noise-reducing unit (10) having a chamber (101), wherein the chamber (101) communicates with an air channel (21) produced by a fan (25)...  
WO/2018/152960A1
Provided is a collision warning method based on control voice information, comprising: collecting radio voice information of a controller and a pilot, and converting the radio voice information to a digital signal using a control seat so...  
WO/2018/154229A1
The invention relates to a percussion bell comprising a bell (1) and a hammer (2) mounted on a base (4) provided with a collar (5) for clamping around a mounting, said collar being arranged to define an installation axis (A') of said mou...  
WO/2018/150972A1
Provided is a soundproof structure which is capable of achieving a sufficient silencing effect with respect to lower frequency sound which resonates in an opening provided in a wall member which divides two spaces. This soundproof struct...  
WO/2018/151129A1
This sound absorbing body is provided with a main body having a bottomed cylindrical shape with an opening portion and a bottom portion, and a porous sheet covering the opening portion. The main body is provided between the opening porti...  
WO/2018/151067A1
Provided is a soundproof structure which is compact, and exhibits high soundproofing performance in a low frequency band. The present invention is provided with at least one soundproof cell provided with: a framework having a hole; an el...  
WO/2018/151717A1
In an example implementation according to aspects of the present disclosure, a method may include identifying, via a first microphone of a device, when a user registered to use the device is speaking, and comparing a voice characteristic...  
WO/2018/149730A1
The invention relates to a diaphragm cup (10) for an ultrasonic transducer (100), comprising a wall (12) for supporting a diaphragm (13), which can be vibrationally excited, the diaphragm cup (10) being provided with merely one single me...  
WO/2018/151772A1
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detecting hotwords using a server. One of the methods includes receiving an audio signal encoding one or more utterances including a firs...  
WO/2018/151464A1
The present invention relates to a coding system and a coding method using voice recognition; and performs natural language processing including morphological analysis, syntactic analysis, semantic analysis, discourse analysis or a combi...  
WO/2018/151106A1
In order to provide a floating speaker that: is capable of oscillating sound in every direction in the surroundings without causing energy loss; and is of a unique, unprecedented design, a speaker emits sound such as music, speech, etc.,...  
WO/2018/151858A1
A method for processing a multi-channel input audio signal is performed at a computing device. The method includes the following steps: selecting, from the multi-channel input audio signal, a left input channel and a right input channel,...  
WO/2018/150825A1
The present invention provides a keyboard harmonica capable of adjusting tones without the need for a complex structure. The aperture ratio of the valve packing 40 of a keyboard harmonica 1 is less than 1 for a midrange SA2 and a high ra...  
WO/2018/151789A1
Techniques for mute pattern injection for a pulse-density modulation microphone are described. In one or more implementations, a pulse-density modulation (PDM) microphone includes a transducer that receives a pressure wave and produces a...  
WO/2018/151399A1
The present invention relates to a sound correction device for producing more beautiful sounds of a wind instrument. More specifically, the present invention relates to a sound correction device for a wind instrument, coupled so as to co...  
WO/2018/151781A1
The present disclosure is directed toward systems and methods for managing a digital survey over voice-capable devices. In particular, the systems and methods described herein create a digital survey question from a verbal input. Additio...  
WO/2018/151125A1
Provided is a word vectorization device for converting a word to a word vector that accounts even for acoustic characteristics of the word. A word vectorization model learning device includes a learning unit that learns a word vectorizat...  
WO/2018/150828A1
The present invention provides a small sound proof structure exhibiting high sound proof performance for lower-frequency sounds. The sound proof structure includes at least one sound proof cell having a frame with a hole and a film secur...  
WO/2018/149401A1
Disclosed are a composite noise-reducing plate and a noise-reducing device. The composite noise-reducing plate comprises a sound absorption layer and a metal sound insulation layer, wherein the sound absorption layer is provided with a s...  
WO/2018/150371A1
A voice activation system for a vehicle. The voice activation system for a vehicle which has at least one sound panel capable of providing vibrations of a user's voice from the outside of the vehicle into an inside area of the vehicle. A...  
WO/2018/149077A1
Provided are a voiceprint recognition method, a device, a storage medium, and a background server. The voiceprint recognition method comprises: a client collecting a test voice of a user, and sending a voice recognition request to a back...  
WO/2018/149285A1
Provided are a voice wake-up method and apparatus, an electronic device, and a storage medium, which belong to the field of voice processing technologies. The method comprises: acquiring a voice signal in a vehicle (201); calculating an ...  
WO/2018/150083A1
The invention relates to a method and technical equipment for media compression/decompression. The method comprises receiving media data (300) for compression; determining, by a first neural network (310), an indication (320) of at least...  

Matches 101 - 150 out of 213,998