Login| Sign Up| Help| Contact|

Patent Searching and Data


Matches 601 - 650 out of 228,319

Document Document Title
WO/2020/211006A1
The present application discloses a speech recognition method. By means of said method, in addition to inputted speech data, an electronic device also uses, in a cooperative manner, context data corresponding to the speech data as auxili...  
WO/2020/213684A1
The present invention relates to a sound-absorbing material comprising, in the following order, a first resin film, a first substrate layer, which has interconnected pores, a second resin film, and a second substrate layer, which has int...  
WO/2020/214281A1
A CS CTC model may be initialed from a major language CTC model by keeping network hidden weights and replacing output tokens with a union of major and secondary language output tokens. The initialized model may be trained by updating pa...  
WO/2020/214658A1
A method for converting text to audio to improve a design of electronic mail messages includes converting, by a text-to-speech converter component executing on a first computing device, an electronic mail message into an audio file. The ...  
WO/2020/212703A1
A method of processing a voice audio signal is provided. The method comprises dividing a voice audio signal into a plurality of segments based on identified spoken phrases within the signal. If it is determined that a selected segment of...  
WO/2020/214252A1
Embodiments are associated with a feature extractor to receive speech frames and extract features based on a first set of parameters of the feature extractor, a senone classifier to identify a senone based on the received features and on...  
WO/2020/213098A1
The purpose of the present invention is to provide a video display device which reduces a sense of discomfort when sharing a space with other people via an avatar, and a display control method for the same. In order to achieve the above ...  
WO/2020/214230A1
A hybrid acoustic silencer for a motor vehicle includes an insertion loss layer tuned for good insertion loss properties at specific frequencies and an absorption layer tuned for good absorption properties at specific frequencies. The in...  
WO/2020/213767A1
A multi-device control method according to an aspect of the present invention comprises the steps of: performing a voice recognition operation on a voice command generated from a sound source; identifying the distance between each of a p...  
WO/2020/214298A1
Embodiments are associated with a speaker-independent acoustic model capable of classifying senones based on input speech frames and on first parameters of the speaker-independent acoustic model, a speaker-dependent acoustic model capabl...  
WO/2020/215089A1
Disclosed herein are system, method, and computer program product embodiments for incorporating a voice command from a user into a game. An embodiment operates by receiving real-time context data of a game and a voice command from a user...  
WO/2020/212419A1
A method for determining a deep filter comprises the following steps: • receiving a mixture; • estimating using a deep neural network the deep filter, wherein the estimating is performed, such that the deep filter, when applying to e...  
WO/2020/212178A1
The invention relates to a method for suppressing noise in audio signals in a vehicle (1), comprising: providing a noise suppression filter (18), which is designed to at least partially suppress a noise component in an audio signal; rece...  
WO/2020/213996A1
A method of detecting an instruction from a user includes receiving, from the user of a user device, an audio input; extracting a non-verbal audio cue or a verbal audio cue based on the audio input; calculating a confidence score based o...  
WO/2020/214752A1
Systems and methods are disclosed for non-invasive detection of chemicals within objects (24). An object (24) comprised of cellulose material is placed inside an examination chamber (20), which is sealed. A first measurement of the speed...  
WO/2020/214844A1
A method of presenting a signal to a speech recognition engine is disclosed. According to an example of the method, an audio signal is received from a user. A portion of the audio signal is identified, the portion having a first time and...  
WO/2020/213245A1
This information processing device comprises: an output control unit that controls the output from an interaction device to a user; a behavior evaluation unit that determines the behavior of the user performed in response to the output o...  
WO/2020/213138A1
The present disclosure pertains to a sound-absorbing material comprising, in the following order: a first resin film; a first substrate layer having communication holes; a second resin film; and a second substrate layer having communicat...  
WO/2020/212673A1
An anonymous audio system, including: at least one user device in network connection with a server, the user device including: a storage; an emotion self-rating module for receiving an audio data associated with an audio and storing the ...  
WO/2020/001568A8
The present application provides a method and apparatus for determining a weighting coefficient during a stereo signal coding process. The method comprises: determining, according to a coding mode of a signal to be coded in a stereo sign...  
WO/2020/214260A1
According to some embodiments, a universal modeling system may include a plurality of domain expert models to each receive raw input data (e.g., a stream of audio frames containing speech utterances) and provide a domain expert output ba...  
WO/2020/211354A1
A speaker identity recognition method and device based on speech content, and a storage medium. The method comprises: acquiring an initial speech signal, wherein the initial speech signal comprises speech content of at least two targets ...  
WO/2020/214006A1
A prompt information processing apparatus and method are provided. The apparatus may include a memory configured to store one or more instructions, and at least one processor configured to execute the one or more instructions stored in t...  
WO/2020/213296A1
Provided is a signal processing device comprising a directivity processing unit that acquires audio signals of a plurality of channels simultaneously collected by a microphone array constituted by a plurality of microphones and that uses...  
WO/2020/214253A1
To generate substantially condition-invariant and speaker-discriminative features, embodiments are associated with a feature extractor capable of extracting features from speech frames based on first parameters, a speaker classifier capa...  
WO/2020/211350A1
Provided are a speech material training method and apparatus, a computer device and a storage medium. The method comprises: determining several general words and several pronunciation regions; determining several first thresholds, wherei...  
WO/2020/214297A1
Embodiments are associated with determination of a first plurality of multi-dimensional vectors, each of the first plurality of multi-dimensional vectors representing speech of a target speaker, determination of a multi-dimensional vecto...  
WO/2020/213140A1
The present disclosure pertains to a sound-absorbing material comprising, in the following order: a first substrate layer having communication holes; an adhesive layer; and a second substrate layer having communication holes.  
WO/2020/213785A1
The present invention relates to a system for automatically generating text-based sentences on the basis of deep learning to achieve an improvement related to the infinity of utterance patterns and, more specifically, to a system for aut...  
WO/2020/212174A1
The bicycle bell (1) includes a bell body (2), a thumb-operated clapper (3) or lever adapted to strike the bell body (2) in order to produce a sound, a frame element (4) holding the bell body and the thumb-operated clapper or lever, and ...  
WO/2020/214988A1
A method and system of audibly broadcasting responses to a user based on user queries about a specific patient molecular report, the method comprising receiving an audible query from the user to a microphone coupled to a collaboration de...  
WO/2020/213427A1
Provided is a command analysis device that is capable of shortening time to command execution. The device comprises: a voice recognition unit that, whenever a voice signal of a prescribed unit is inputted, performs voice recognition upon...  
WO/2020/213139A1
The present disclosure pertains to a sound-absorbing material comprising, in the following order: a resin film; a first substrate layer having communication holes; and a second substrate layer having communication holes.  
WO/2020/214259A1
Embodiments are associated with conditional teacher-student model training. A trained teacher model configured to perform a task may be accessed and an untrained student model may be created. A model training platform may provide trainin...  
WO/2020/212390A1
Dialogue enhancement of an audio signal, comprising obtaining a set of time-varying parameters configured to estimate a dialogue component present in said audio signal, estimating the dialogue component from the audio signal, applying a ...  
WO/2020/214373A1
Methods and apparatus for detecting audio anomalies from a reference audio file and a sampled audio filed. In embodiments, a system can perform aligning in time first and second audio files, dividing the first and second audio files into...  
WO/2020/213676A1
The present disclosure pertains to a sound-absorbing material comprising, in the following order, a resin film, a first substrate layer having communication holes, and a second substrate layer having communication holes.  
WO/2020/213758A1
Provided according to an embodiment of the present invention is a speech-interactive artificial intelligence device comprising: a microphone which acquires audio data corresponding a user's utterance; a memory which stores a first platfo...  
WO/2020/001570A8
Provided are a stereo signal coding method and apparatus and decoding method and apparatus. The coding method comprises: performing spectrum spreading on a quantized LSF parameter of a primary channel signal of a current frame in a stere...  
WO/2020/211806A1
The present application aims to provide a method for providing a rescue voice prompt. The method comprises: if a prompt termination condition is not satisfied, a wearable rescue device collecting voice information of a rescued object at ...  
WO/2020/212544A1
The invention relates to a public transportation vehicle with a sanitary cell with at least one electrically or electronically actuatable device and at least one microphone for detecting speech signals of a user, wherein the vehicle has ...  
WO/2020/214269A1
A method (800) includes receiving audio data (125) of an utterance (120) and processing the audio data to obtain, as output from a speech recognition model (140) configured to jointly perform speech decoding and endpointing of utterances...  
WO/2020/213685A1
The present disclosure pertains to a sound absorbing material comprising, in the following order: a first substrate layer having a communication hole; an adhesive layer; and a second substrate layer having a communication hole.  
WO/2020/208926A1
A signal processing device having: an input unit to which a microphone signal and a one-dimensional time series signal are inputted, said microphone signal including a mixed sound in which a target sound and a sound other than the target...  
WO/2020/208859A1
A chatbot management device which manages a bot to be stored in a primary storage unit in a chat system, said device comprising: an acquisition unit which acquires chat scenario information wherein operations of bots are described; a met...  
WO/2020/207596A1
The invention is related to the technical field of audio recording of 3D sound, for instance, for virtual reality (VR) or surround sound. The invention relates to VR compatible audio formats, i.e. First Order Ambisonic (FOA) signals. The...  
WO/2020/209840A1
The present disclosure describes techniques for adding a perception of directionality to audio. The method includes training an artificial neural network using a binary encoded set of head related transfer function (HRTF) angle values to...  
WO/2020/207593A1
An audio decoder for providing a decoded audio representation on the basis of an encoded audio representation comprises a filter for providing an enhanced audio representation of the decoded audio representation. The filter is configured...  
WO/2020/208811A1
This reproduction control device (100) comprises: an audio processing section determination unit (120) which determines, on the basis of lyrics data (111) associated with reproduction position information (111T) on a musical piece, an au...  
WO/2020/209647A1
Disclosed is a method for generating synthetic speech for text through a user interface. The method can comprise the steps of: receiving at least one sentence; determining a speech style characteristic for the received at least one sente...  

Matches 601 - 650 out of 228,319