Lg Electronics Inc.

Korea Institute of Science and Technology

Vsi Corporation

Sungmin Han

Siyoung Yang

Yongchul Park

Juyeong Jang

Minook Kim

Sangki Kim

Jonghoon Chae

Wonho Shin

Inchan Youn

Jong Hoon Chae

Suwon Kang

Sang Ki Kim

Choong Hyun Kim

Hwansik Yun

Song Joo Lee

Sung Rock Lee

Provided is a speech synthetic device capable of outputting a synthetic voice having various speech styles. The speech synthesis device includes a speaker, and a processor to acquire voice feature information through a text and a user input; generate a synthetic voice, by receiving the text and the voice feature information inputs into a decoder supervised-trained to minimize a difference between feature information of a learning text and characteristic information of a learning voice, and output the generated synthetic voice through the speaker.

Speech synthesis device and speech synthesis method

The training apparatus according to an embodiment includes: a support unit; a guide unit fixed on the support unit and including rails which extend in a front-rear direction; a sliding unit which is movable in the front-rear direction along the rails of the guide unit; a pillar-shaped rotation axis fixed on the support unit; a footrest unit which supports a user's foot; a lower support formed below the footrest unit; and a connection rotating unit formed below the footrest unit and connected to the rotation axis of the support unit through insertion to allow the footrest unit to rotate around the rotation axis. A plurality of springs installed inward from two sidewalls of the sliding unit is configured to come into contact with the lower support of the footrest unit and apply pressure from two sides when the footrest unit rotates.

Training apparatus for improving control ability of lower limb

An artificial intelligence device includes a memory and a processor. The memory is configured to store audio data having a predetermined speech style. The processor is configured to generate a condition vector relating to a condition for determining the speech style of the audio data, reduce a dimension of the condition vector to a predetermined reduction dimension, acquire a sparse code vector based on a dictionary vector acquired through sparse dictionary coding with respect to the condition vector having the predetermined reduction dimension, and change a vector element value included in the sparse code vector.

Artificial intelligence device and method for generating speech having a different speech style

Disclosed is a device for controlling a plurality of voice recognition devices for determining and selecting a first voice recognition device that a user wants to use based on a point in time when the voice of the user is spoken or a place where the user spoke the voice. The device for controlling a plurality of voice recognition devices according to the present disclosure may be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to 5G service, etc.

Device, system and method for controlling a plurality of voice recognition devices

A method and apparatus for controlling a device according to an embodiment of the present disclosure may be based on a speech feature of a user reflecting the Lombard effect so as to operate a device located far away from the user, among a plurality of electronic devices. As such, even when the user calls a device located far away from the user without any separate context information, speech recognition neural networks and weight calculation neural networks may be selected and used to operate the device located far away from the user, and reception of a speech signal of the user calling a device located far away from the user may be performed in an Internet of Things (IoT) environment using a 5G network.

Method and apparatus for controlling device located a distance away from a user

According to one embodiment, an apparatus for processing a voice signal includes a display configured to display an image of a user or a character corresponding to the user, a microphone, a speaker configured to output a voice signal of the user, a memory configured to store a trained voice age conversion model, and a processor configured to, based on changing an age of the user or the character displayed on the display, control the display such that the display displays the user or the character corresponding to the changed age. The processor is further configured to determine a first age that is a current age of the user or the character based on the voice signal of the user inputted through the microphone. Accordingly, convenience of a user may be enhanced.

Apparatus for voice-age adjusting an input voice signal according to a desired age

A method includes generating first synthesized speech by using text and a first emotion vector configured for the text, extracting a second emotion vector included in the first synthesized speech, determining whether correction of the second emotion information vector is needed by comparing a loss value calculated by using the first emotion information vector and the second emotion information vector with a preconfigured threshold, re-performing speech synthesis by using a third emotion information vector generated by correcting the second emotion information vector, and outputting the generated synthesized speech, thereby configuring emotion information of speech in a more effective manner. A speech synthesis apparatus may be associated with an artificial intelligence module, drone (unmanned aerial vehicle, UAV), robot, augmented reality (AR) devices, virtual reality (VR) devices, devices related to 5G services, and the like.

Method for synthesized speech generation using emotion information correction and apparatus

A voice recognition device and a method for learning voice data using the same are disclosed. The voice recognition device combines feature information for various speakers with a text-to-speech function to generate voice data recognized by a voice recognition unit, and can improve voice recognition efficiency by allowing the voice recognition unit itself to learn various voice data. The voice recognition device can be associated with an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, devices related to 5G services, and the like.

Voice recognition device and method for learning voice data

An electronic device is disclosed. The electronic device includes a memory and a processor. The electronic device may execute an artificial intelligence (AI) algorithm and/or a machine learning algorithm, and perform communications with other electronic devices in a 5G communication network. Accordingly, user convenience can be significantly improved.

Electronic apparatus and method for operating the same

Disclosed is gathering a user's speech samples. According to an embodiment of the disclosure, a method of gathering learning samples may gather a speaker's speech data obtained while talking on a mobile terminal and text data generated from the speech data and gather training data for generating a speech synthesis model. According to the disclosure, the method of gathering learning samples may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

Gathering user's speech samples

Disclosed are an emotion classification information-based text-to-speech (TTS) method and device. The emotion classification information-based TTS method according to an embodiment of the present invention may, when emotion classification information is set in a received message, transmit metadata corresponding to the set emotion classification information to a speech synthesis engine and, when no emotion classification information is set in the received message, generate new emotion classification information through semantic analysis and context analysis of sentences in the received message and transmit the metadata to the speech synthesis engine. The speech synthesis engine may perform speech synthesis by carrying emotion classification information based on the transmitted metadata.

Emotion classification information-based text-to-speech (TTS) method and apparatus

Disclosed is speech synthesis in a noisy environment. According to an embodiment of the disclosure, a method of speech synthesis may generate a Lombard effect-applied synthesized speech using a feature vector generated from an utterance feature. According to the disclosure, the speech synthesis method and device may be related to artificial intelligence (AI) modules, unmanned aerial vehicles (UAVs), robots, augmented reality (AR) devices, virtual reality (VR) devices, and 5G service-related devices.

Speech synthesis in noisy environment

A speech synthesizer includes a memory configured to store a plurality of sentences and prior information of a word classified into a minor class among a plurality of classes with respect to each sentence, and a processor configured to determine an oversampling rate of the word based on the prior information, determine the number of times of oversampling of the word using the determined oversampling rate and generate sentences including the word by the determined number of times of oversampling. The plurality of classes includes a first class corresponding to first reading break, a second class corresponding to second reading break greater than the first break and a third class corresponding to third reading break greater than the second break, and the minor class has a smallest count among the first to third classes in one sentence.

Speech synthesizer using artificial intelligence, method of operating speech synthesizer and computer-readable recording medium

A speech synthesizer using artificial intelligence includes a memory configured to store a first ratio of a word classified into a minor class among a plurality of classes, a second ratio of the word which is not classified into the minor class, and a synthesized speech model and a processor configured to change a first class classification probability set of the word to a second class classification probability set, based on the first ratio, the second ratio and the first class classification probability set, and learn the synthesized speech model using the changed second class classification probability set.

Disclosed is a device that multiplies a first signal outputted from a CTLE and a second signal obtained by delaying the first signal by a predetermined time interval; produces a specific signal reflecting a temporal sum of the multiplied signal; determines gain control signal in a manner such that the difference between the specific signal and a predetermined target level is reduced; and provides the determined gain control signal to the CTLE so as to be applied to high-band boosting thereof. The time interval to be delayed corresponds to N (N is an integer equal to or greater than one) times a unit interval that is occupied by one symbol in the first signal.

Growing community of inventors

Seoul, South Korea

Sungmin Han