Samsung Electronics Co., Ltd.

Lg Innotek Co., Ltd.

Ki Soo Kwon

Il Yeong Kang

Tae Young Choi

Sanghyun Yoo

Minyoung Mun

Sang Hoon Lee

Jeong-Hoon Park

Young Jin Kim

Keun Tak Joo

Min Hak Kim

Hoshik Lee

Do Yub Kim

Hodong Lee

Young Sang Choi

Jong Chan Park

Inchul Song

Jae Hun Yoon

YoungSang Choi

Eon Ho Son

Seung Beom Jeong

A processor-implemented model training method and apparatus are provided. The method calculates an entropy of each of a plurality of previously trained models based on training data, selects a previously trained model from the plurality of previously trained models based on the calculated entropy, and trains a target model, distinguished from the plurality of previously trained models, based on the training data and the selected previously trained model.

Apparatus and method with model training

A method and apparatus for personalizing a speech recognition model is disclosed. The apparatus may obtain feedback data that is a result of recognizing a first speech input of a user using a trained speech recognition model, determine whether to update the speech recognition model based on the obtained feedback data, and selectively update, dependent on the determining, the speech recognition model based on the feedback data.

Method and apparatus with a personalized speech recognition model

A processor-implemented speech recognition method includes: applying, to an input layer of a neural network, a frame of a speech sequence; obtaining an output of a hidden layer of the neural network corresponding to the frame; calculating a statistical value of at least one previous output of the hidden layer corresponding to at least one previous frame of the speech sequence; normalizing the output based on the statistical value; applying the normalized output to a subsequent layer of the neural network; and recognizing the speech sequence based on the applying of the normalized output.

Apparatus and method with speech recognition and learning

A processor-implemented method of personalizing a speech recognition model includes: obtaining statistical information of first scaling vectors combined with a base model for speech recognition; obtaining utterance data of a user; and generating a personalized speech recognition model by modifying a second scaling vector combined with the base model based on the utterance data of the user and the statistical information.

Speech recognition apparatus and method

Provided is a method and device to personalize a speech recognition model, the device that personalizes a speech recognition model by identifying a language group corresponding to a user, and generating a personalized speech recognition model by applying a group scale matrix corresponding to the identified language group to at least a layer of a speech recognition model.

Device and method to personalize speech recognition model

A speech signal recognition method, apparatus, and system. The speech signal recognition method may include obtaining by or from a terminal an output of a personalization layer, with respect to a speech signal provided by a user of the terminal, having been implemented by input of the speech signal to the personalization layer, the personalization layer being previously trained based on speech features of the user, implementing a global model by providing the obtained output of the personalization layer to the global model, the global model being configured to output a phonemic signal indicating a phoneme included in the speech signal through the global model being previously trained based on speech features common to a plurality of users, and re-training the personalization layer based on the phonemic signal output from the global model, where the personalization layer and the global model collectively represent an acoustic model.

Speech signal recognition system and method

A light emitting module of an embodiment comprises: (1-1)to (1-M)(where M is a positive integer equal to or greater than 2) light emitting elements connected with each other; (2-1)to (2-N)(where N is a positive integer equal to or greater than 1) light emitting elements connected in parallel with a (1-m)(1&#x2264;m&#x2264;M) light emitting elements which is one of the (1-1)to (1-M)light emitting elements; and an on/off controller controlling to turn the (1-1)to (1-M)light emitting elements and (2-1)to (2-N)light emitting elements on or off according to a level of an operation signal. The on/off controller comprises a first on/off control unit controlling to turn the (1-m)light emitting element and (2-1)to (2-N)light emitting elements on or off, and a second on/off control unit controlling to turn the remaining light emitting elements on or off, excluding the (1-m)light emitting element from the (1-1)to (1-M)light emitting elements, wherein the first on/off control unit compensates for a change in a second current flowing in the (2-1)to (2-N)light emitting elements, depending on the temperature, in conjunction with a first current flowing in the (1-m)light emitting element.

Light emitting module

A light emitting module includes a plurality of light emitting device packages configured to be sequentially turned on or off according to the level of external drive voltage and connected to one another in series. Each of the plurality of light emitting device packages includes a light emitting cell having at least one light emitting device, and an on/off controller configured to control to turn the light emitting cell on or off.

Embodiments provide a light emitting module including a body, a plurality of light emitting devices disposed on the body, and a turn-on controller configured to control turn-on of the plurality of light emitting devices. At least some neighboring light emitting devices among the plurality of light emitting devices are spaced apart from one another by different distances.

A light emitting unit includes a plurality of light emitting devices. A control apparatus includes a rectifier for converting an alternating current (AC) signal into a ripple signal by rectifying the AC signal. A ripple signal adjuster reduces a level difference between maximum and minimum levels of the ripple signal, and outputs the resultant ripple signal as a drive signal. A turning-on controller controls turning-on of the light emitting devices in accordance with a level variation of the drive signal.

Growing community of inventors

Seoul, South Korea

Ki Soo Kwon