Login| Sign Up| Help| Contact|

Patent Searching and Data


Matches 151 - 200 out of 212,053

Document Document Title
WO/2018/053531A1
In a speaker recognition apparatus, audio features are extracted from a received recognition speech signal, and first order Gaussian mixture model (GMM) statistics are generated therefrom based on a universal background model that includ...  
WO/2018/052557A1
Methods and apparatuses are disclosed for streaming audio between a source device and a destination device. An example method may include determining an available bandwidth between the source device and the destination device. The exampl...  
WO/2018/049510A1
An isolating assembly, a modular isolating system including the assembly and a method of using the same. The system includes a plurality of individual isolating assemblies, each isolating assembly being engageable with an article; and wh...  
WO/2018/053537A1
Utterances of at least two speakers in a speech signal may be distinguished and the associated speaker identified by use of dianzation together with automatic speech recognition of identifying words and phrases commonly in the speech sig...  
WO/2018/049391A1
Method and apparatus for segmenting speech by detecting the pauses between the words and/or phrases, and to determine whether a particular time interval contains speech or nonspeech, such as a pause.  
WO/2018/048268A1
Disclosed are a method and apparatus for selecting and connecting a gateway by a user device using a Bluetooth low energy technology, and a voice recognition system comprising a first device, a first gateway, and a voice recognition serv...  
WO/2018/046546A1
The invention relates to an apparatus (1) for producing haptic feedback, having a piezoelectric actuator (2) and a mechanical structure (3), wherein the piezoelectric actuator (2) is designed to change the extent thereof in a first direc...  
WO/2018/049313A1
The present invention is directed to a deep neural network (DNN) having a triplet network architecture, which is suitable to perform speaker recognition. In particular, the DNN includes three feed-forward neural networks, which are train...  
WO/2018/049282A1
Speech in a motor vehicle is improved by suppressing transient, "non-stationary" noise using pattern matching. Pre-stored sets of linear predictive coefficients are compared to LPC coefficients of a noise signal. The pre-stored LPC coeff...  
WO/2018/047932A1
An interactive device equipped with: an interaction start condition determination unit for determining whether or not acquired first acquisition information matches an interaction start condition; an analysis unit for performing an analy...  
WO/2018/049279A1
A frequency domain long-term prediction system and method for estimating and applying an optimum long term predictor. Embodiments of the system and method include determining parameters of a single-tap predictor using a frequency- domain...  
WO/2018/047153A1
The acoustic metamaterial sound absorber (10, 100, 300, 400, 500, 600, 700, 800, 900, 1000) is formed from an array of acoustic resonance cavities (310, 410). Each of the acoustic resonance cavities (310, 410) may be folded to have at le...  
WO/2018/047578A1
This keyboard device is provided with white keys, black keys adjacent to white keys, and guides arranged between the white keys and black keys and contacting each of the white keys and black keys to restrict action thereof. A housing tha...  
WO/2018/047275A1
The objective of the invention is to match the output timing of speech with a character display timing. A speech storage data acquisition means (100) of a display timing determination apparatus (10, 20) acquires speech storage data in wh...  
WO/2018/047436A1
A translation device is provided with an input unit and a control unit. The input unit acquires first text data of a first language. The control unit generates second text data of a second language which is a parallel translation of the ...  
WO/2018/047890A1
The present invention arranges a plurality of ordinary display devices having only one display screen side by side and browses a plurality of pages of a document or a musical score simultaneously. When an indication for delivery of a mus...  
WO/2018/046185A1
Embodiments of the present invention provide an in-vehicle privacy system, comprising audio output means (146, 147) associated with a first zone (110) of an interior of a vehicle (100), audio source means (250) for providing an audio sig...  
WO/2018/046088A1
A device has an input that is configured to receive a sound signal captured from an acoustic environment in which the device is located. The device also includes a signal processor that is configured to obtain a reverberation signature f...  
WO/2018/046859A1
The invention relates to a method for filtering an amplitude-modulated radio signal (AM1), said radio signal having a bandwidth, the method comprising the steps of: converting the radio signal into a baseband signal; determining a freque...  
WO/2018/047790A1
A synthesized reference signal generating unit provided in an active noise reducing device has a plurality of filters each adapted to one of a plurality of reference signals that are input and an adding unit for generating a synthesized ...  
WO/2018/048866A1
Examples are disclosed for responding to voice commands within an existing telephony call between two or more end user communication devices mediated by an IP based communications server. The server is mediating a telephony call among th...  
WO/2018/047421A1
[Problem] To obtain a more precise degree of certainty for estimated word strings. [Solution] A speech processing device includes a word string estimation unit for estimating a word string that corresponds to an input speech among the wo...  
WO/2018/048549A1
Systems, articles, and methods include techniques of automatic speech recognition using posterior confidence scores. The method comprises receiving a plurality of frames of an audio sequence with audio data of human speech, wherein indiv...  
WO/2018/045479A1
Plucked string musical instrument with selectively detachable neck, with a resonating body (1) and a neck (2) that can be selectively attached. The resonating body (1) has a recess (10) defining a dovetail performed on a block (19) arran...  
WO/2018/047643A1
This technology relates to a device and method for sound source separation and a program with which higher separation performance can be obtained. The sound source separation device is provided with a combining unit that combines a first...  
WO/2018/047667A1
The present feature relates to a sound processing device and method with which it is possible to reproduce a content with high realistic sensations requiring a small computation or transmission amount. The sound processing device is prov...  
WO/2018/047579A1
This attachment structure is provided with: a first member which includes an attachment part comprising a flexible part and an engagement part provided on one end of the flexible part; and a second member on which the first member is mou...  
WO/2018/048211A1
The present invention relates to a thumb rest protector. The present invention provides a thumb rest protector configured to easily cover the thumb rest of a musical instrument, thereby protecting the player's thumb more effectively, pre...  
WO/2018/047526A1
An electronic acoustic device 1 is provided with a control operation element 21 (for example a joystick) for adjusting prescribed control parameters (for example acoustic effect parameters) of an acoustic signal. The electronic acoustic ...  
WO/2018/048907A1
A method for providing information to a user, the method including: receiving an input signal from a sensing device associated with a sensory modality of the user; generating a preprocessed signal upon preprocessing the input signal with...  
WO/2018/048567A1
Techniques are described for assisting near distance communications. A first device comprising a receiver, a sensor and a processor may be configured to perform the assisted near distance communication techniques. The receiver may receiv...  
WO/2018/045988A1
A method and device for generating a digital music score file of a song, and a storage medium. The method comprises: obtaining a candidate cappella audio file satisfying a first condition from cappella audio files corresponding to a song...  
WO/2018/042088A1
This frog (4) for the bow of bowed string instruments comprises a base or body, – of which the upper part (7), referred to as the slide has a cross section of concave shape intended to accept the correspondingly-shaped end (6) of the s...  
WO/2018/045119A1
The technology described in this document can be embodied in a computer-implemented method that includes presenting a first user-interface that includes a user-selectable menu of multiple virtual personal assistant (VPA) service provider...  
WO/2018/039811A1
The invention relates to a device for securing musical instruments, such as guitars, bass guitars and similar, the device comprising a strap or loop having retractable means disposed at the first end thereof, and a means for attaching an...  
WO/2018/041987A1
An ultrasound probe (106) contains an array transducer (101) and a microbeamformer coupled to elements of the array. The microbeamformer comprises analog ASICs (102) with transmitters and amplifiers coupled to elements of the array (101)...  
WO/2018/042094A1
The invention concerns a shield (1) comprising: a shell (3) with a moulded appearance made from polyurethane foam with a density of between 0.38 and 0.42, the front face (4) of said shell having no coating, so as to form a visible face o...  
WO/2018/043137A1
The present technology relates to an information processing device and an information processing method capable of quickly acquiring desired voice recognition results. The information processing device includes a voice recognition unit f...  
WO/2018/040102A1
An audio processing method, comprising: determining an audio data source and carrying out audio interception service registration on the audio data source to obtain audio interception service registration information (S610), the audio in...  
WO/2018/043113A1
This technology pertains to an information processing apparatus, an information processing method, and a program, which enable information to be presented to a user while protecting privacy. This technology is provided with: an extractio...  
WO/2018/043895A1
Provided are a display device and a screen display method for of the display device. In detail, disclosed are a display device capable of controlling a screen thereof through voice recognition, and a screen display method of the display ...  
WO/2018/041956A1
The invention relates to a method for changing the noise emission (200) of an entrance system for a rail vehicle, wherein in an excitation step at least one partial region (206) of the entrance system is actively vibrationally excited by...  
WO/2018/044915A1
In at least one embodiment, an apparatus for generating virtual venues in a listening room in a vehicle is provided. The apparatus includes a vehicle audio controller configured to receive an incoming audio signal including entertainment...  
WO/2018/040983A1
A method for transmitting navigation information, comprising: receiving audio information needing to be transmitted, the audio information comprising navigation information (S101); converting the navigation information into navigation in...  
WO/2018/045259A1
Systems and methods for optimizing the working environment in a drilling control room may include (i) systems and methods to selectively actively attenuate one or more noise sources affecting the noise level within the drilling control r...  
WO/2018/042773A1
[Problem] To suppress musical noise and the like when area sound pickup is performed. [Solution] The present invention relates to a sound pickup device. This sound pickup device is characterized by being provided with: a directivity form...  
WO/2018/043917A1
The present invention relates to adjusting audio. In accordance with one embodiment, an audio is received on an electronic device from at least one audio source. At least one first audio parameter and a target audio is extracted from the...  
WO/2018/041238A1
A hydrophone (100, 300) and compound hydrophones (200, 400, 500) made of the hydrophone (100, 300) comprises at least one strip-like transduction element (110, 311), a shell (120) or housing (122), sound-permeable sealing sheet (130, 140...  
WO/2018/040341A1
Provided are an artificial intelligence-based information notification method and device. The method comprises: converting acquired speech information into text information (201); extracting, from the text information, notification infor...  
WO/2018/040947A1
Disclosed in the present application are a user positioning method and apparatus. By identifying an audio signal having a watermark and acquired at a client end, accurate positioning of a user can be achieved without operations such as t...  

Matches 151 - 200 out of 212,053