公开(公告)号：US20160055846A1

公开(公告)日：2016-02-25

申请号：US14465001

申请日：2014-08-21

Applicant: Electronics and Telecommunications Research Institute

Inventor： Ho-Young JUNG ,  Hwa-Jeon SONG

IPC: G10L15/20

CPC classification number: G10L15/20 ,  G10L15/065

Abstract: A method for speech recognition in accordance with the present invention includes: extracting a speech feature from an inputted speech signal; estimating a noise component of the speech signal; compensating the extracted speech feature by use of the estimated noise component; transforming a given acoustic model based on the extracted speech feature, the compensated speech feature, and the noise component; and performing speech recognition by use of the compensated speech feature and the transformed acoustic model.

Abstract translation: 根据本发明的用于语音识别的方法包括：从输入的语音信号中提取语音特征; 估计语音信号的噪声分量; 通过使用所估计的噪声分量补偿所提取的语音特征; 基于提取的语音特征，补偿语音特征和噪声分量来变换给定的声学模型; 以及通过使用经补偿的语音特征和变换的声学模型来执行语音识别。

公开(公告)号：US20240232648A1

公开(公告)日：2024-07-11

申请号：US18537588

申请日：2023-12-12

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hyun-Woo KIM ,  Hwa-Jeon SONG ,  Jeong-Min YANG ,  Byung-Hyun YOO ,  Eui-Sok CHUNG ,  Ran HAN

IPC: G06N3/0985 ,  G06N3/0455 ,  G06N3/088

CPC classification number: G06N3/0985 ,  G06N3/0455 ,  G06N3/088

Abstract: Disclosed herein are a multimodal unsupervised meta-learning method and apparatus. The multimodal unsupervised meta-learning method includes training, by a multimodal unsupervised feature representation learning unit, an encoder configured to extract features of individual single-modal signals from a source multimodal dataset, generating, by a multimodal unsupervised task generation unit, a source task based on the features of individual single-modal signals, deriving, by a multimodal unsupervised learning method derivation unit, a learning method from the source task using the encoder, and training, by a target task performance unit, a model based on the learning method and features extracted from a small number of target datasets by the encoder, thus performing the target task.

公开(公告)号：US20140163986A1

公开(公告)日：2014-06-12

申请号：US14095622

申请日：2013-12-03

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sung-Joo LEE ,  Ho-Young JUNG ,  Hwa-Jeon SONG ,  Eui-Sok CHUNG ,  Byung-Ok KANG ,  Hoon CHUNG ,  Jeon-Gue PARK ,  Hyung-Bae JEON ,  Yoo-Rhee OH ,  Yun-Keun LEE

IPC: G10L15/02

CPC classification number: G10L15/00 ,  G06F21/31 ,  G06F2221/2133 ,  G10L17/00

Abstract: Disclosed herein is a voice-based CAPTCHA method and apparatus which can perform a CAPTCHA procedure using the voice of a human being. In the voice-based CAPTCHA) method, a plurality of uttered sounds of a user are collected. A start point and an end point of a voice from each of the collected uttered sounds are detected and then speech sections are detected. Uttered sounds of the respective detected speech sections are compared with reference uttered sounds, and then it is determined whether the uttered sounds are correctly uttered sounds. It is determined whether the uttered sounds have been made by an identical speaker if it is determined that the uttered sounds are correctly uttered sounds. Accordingly, a CAPTCHA procedure is performed using the voice of a human being, and thus it can be easily checked whether a human being has personally made a response using a voice online

Abstract translation: 本文公开了一种基于语音的CAPTCHA方法和装置，其可以使用人的声音执行人机验证程序。 在基于语音的CAPTCHA）方法中，收集用户的多个发出的声音。 检测来自每个收集到的发出的声音的声音的起始点和终点，然后检测语音部分。 将各个检测到的语音部分的被调节的声音与参考发出的声音进行比较，然后确定发出的声音是否被正确发出的声音。 如果确定发出的声音被正确发出声音，则确定发声是否由相同的扬声器发出。 因此，使用人的声音执行人机识别程序，因此可以容易地检查人是否已经使用在线语音亲自作出了响应