Actionpower Corp.

Hyundai Motor Company

Kia Corporation

Dongchan Shin

Jihwa Lee

Subong Choi

Seongmin Park

Hwanbok Mun

Sangyoun Paik

Seung Jae Lee

Hyungwoo Kim

Alena Kazakova

Gyujin Kim

An electronic toll collection system terminal includes a communication interface configured to be connected to a vehicle network, a card IC chip configured to store a first card issued, and a controller configured to control the communication interface and the card IC chip. The controller is configured to generate initialization inter-sector electronic purse data of the first card, control the communication interface to transmit the initialization IEP data of the first card to a roadside equipment of the tollgate in response to the vehicle approaching a tollgate in a state where of new issuance of a second card is being requested, and control the communication interface to perform billing communication with the RSE using the first card and, in response to the vehicle passing the tollgate, control the communication interface to switch to the state where of new issuance of the second card is being requested.

Electronic toll collection system and control method for the same

Disclosed is a pronunciation transcription method performed by a computing device. The method may include: acquiring a partial audio signal of a first sound unit generated by splitting an audio signal; inputting the partial audio signal of the first sound unit into a pronunciation transcription model; and outputting a pronunciation transcription result for the partial audio signal of the first sound unit by using the pronunciation transcription model.

Method for pronunciation transcription using speech-to-text model

Disclosed is a method for detecting a speech segment, which is performed by a computing device. The method may include: detecting a start point of a speech segment in an audio signal; and detecting an end point of the speech segment based on an offset threshold which is dynamically changed, and the dynamically changed offset threshold may be based on a length of the speech segment.

Method for detecting speech segment from audio considering length of speech segment

Disclosed is a method for detecting a voice from audio data, performed by a computing device according to an exemplary embodiment of the present disclosure. The method includes obtaining audio data; generating image data based on a spectrum of the obtained audio data; analyzing the generated image data by utilizing a pre-trained neural network model; and determining whether an automated response system (ARS) voice is included in the audio data, based on the analysis of the image data.

Method for detecting speech in audio data

Disclosed is a method for error detection, performed by one or more processors of a computing device according to an example embodiment of the present disclosure. The method includes evaluating an error rate for a sentence to be evaluated, in a first language unit. the method includes evaluating an error rate in a second language unit which is smaller than the first language unit, based on the first language unit error.

Method for error detection by using top-down method

Disclosed is a method for speech recognition performed by one or more processors of a computing device. The method includes inputting voice information into an encoder to extract a first feature vector and calculating a first loss function. The method includes inputting the first feature vector extracted from the encoder to a first decoder to perform prediction on the voice information, calculating a second loss function, and extracting a second feature vector. The method includes inputting a second feature vector extracted from the first decoder to a second decoder to perform grapheme-based prediction, and calculating a third loss function. The method includes training at least one of the encoder, the first decoder, or the second decoder based on the first loss function, the second loss function, and the third loss function.

Method for speech recognition with grapheme information

Disclosed is a method for generating data, the method is performed by one or more processors of a computing device. The method may include: segmenting text data generated based on speech information into a token unit; generating a first feature vector based on the text data segmented into the token unit, and generating a first label vector corresponding to the generated first feature vector, and generating a second feature vector and a second label vector by performing mix-up for each of the generated first feature vector and the generated first label vector.

Method for generating learning data for speech recognition error detection

Disclosed is a speech recognition method performed by one or more processors of a computing device, the speech recognition method including: performing first speech recognition on voice information to obtain first text information on the voice information; receiving feedback regarding the first text information; and generating final text information for the voice information based on the received feedback, in which the first speech recognition includes real-time speech recognition, and is performed through a neural network model of a first structure.

Growing community of inventors

Seoul, South Korea

Dongchan Shin