Novel Deep Learning-Based Vocal Biomarkers for Stress Detection in Koreans
Psychiatry InvestigationJournal
인용 6
본 연구는 한국인 대상의 음성 기반 정신 스트레스 평가의 가능성을 강조하며, 다양한 언어 인구집단에서 음성 바이오마커에 대한 지속적인 연구의 중요성을 제시합니다.
AI 생성원문 보기
연구실 정보를 불러오고 있습니다
Nam-Soo Kim
서울대학교 전기정보공학부
인공지능, 음성음향신호처리
nkim@snu.ac.kr
Established in 1998 and directed by Prof. N.S.Kim, the Human Interface Laboratory conducts research on speech and audio signal processing. Current ongoing research topics include speech recognition, speech synthesis, speech enhancement, realistic acoustics, acoustic event detection, audio source seperation, and audio source localization with applications from machine learning.
Core research area covering automatic speech recognition, speech synthesis, speech enhancement, and speech coding for human-machine interface systems.
The task of converting speech utterance into text. ASR is a core technique of human-machine interface system with applications in smart home and phone interfaces.
Technique of synthesizing text input into speech, actively used in smartphone interfaces, personal assistants, ARS, and robot interfaces.
Improves degraded speech intelligibility and quality using audio signal processing techniques. Applications include mobile systems, hearing aids, and ASR.
Application of data compression of digital audio signals containing speech to minimize transmission bandwidth or reduce storage costs.
Research on implementing algorithms for machine learning applications in speech and audio signal processing, including HMM, SVM, DNN, and NMF techniques.
Implements algorithms allowing machines to perform human-like tasks including automatic speech recognition, machine hearing, dialogue systems, and auditory scene understanding.
Provides computers with ability to learn and analyze data without explicit programming. Leading field utilizing machine learning techniques in speech/audio signal processing.
Research area covering realistic audio technology, audio scene recognition, acoustic localization, sound code, and audio source separation.
Method for reproducing spatial sound using recorded anechoic sound sources and measured room impulse responses. Applications include 3D realistic audio systems.
Computational analysis of acoustic environment and recognition of distinct sound events, focusing on recognizing context and analyzing discrete sound events.
Studies localization or tracking of acoustic sources based on sound field measurements. Applications include virtual tour guides, item tracking, and shopping mall navigation.
Wireless data transmission system encoding data using audio data hiding technology. Applications include inserting product information and coupon codes into advertisements.
Technique of extracting single or several signals of interest from mixture signals, removing unwanted components from recordings.
출처: 연구실 홈페이지
현재 재학생
0명
최근 5년 졸업
0명
본 페이지는 연구실 규모 파악을 위한 집계 통계(구성원 수, 진로 카테고리, 학위 과정 분포)만 제공하며, 개별 학생의 이름·전적·취업처 등은 표시하지 않습니다. 학위 과정 분포는 모든 재학생의 과정이 명확히 분류된 경우에만 표시되며 (분류 미상 학생이 1명이라도 있으면 미표시), k≥5 익명성 조건을 충족할 때만 공개됩니다 (PIPA §58-2·§28-2 + 대법원 2014다235080).
본 연구는 한국인 대상의 음성 기반 정신 스트레스 평가의 가능성을 강조하며, 다양한 언어 인구집단에서 음성 바이오마커에 대한 지속적인 연구의 중요성을 제시합니다.
논문 데이터가 수집되면 연구 키워드가 자동 추출됩니다