[논문리뷰] Ensemble knowledge distillation of self-supervised speech models 요약
Ensemble knowledge distillation of self-supervised speech models 요약.pdf
Speech signal processing
SV56 사용 결과 비교
SV56 사용 결과 비교.pdf
Contributions of “A Statistical Model-Based Voice Activity Detection
Contributions of “A Statistical Model-Based Voice Activity Detection.pdf
Contribution of “PEFAC – A Pitch Estimation Algorithm Robust to High Levels of Noise”
Contribution of “PEFAC – A Pitch Estimation Algorithm Robust to High Levels of Noise”.pdf
Contributions of “Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator”
Contributions of “Speech enhancement using a minimum-mean square error short-time spectral amplitude estimator”.pdf
[논문리뷰] Modifying Flow Matching for Generative Speech Enhancement
[논문리뷰] Modifying Flow Matching for Generative Speech Enhancement.pdf
GIST, 플로우 매칭 기반 음성향상 모델의 성능 및 속도 개선
신종원 교수 연구팀 플로우 매칭 기반 음성향상 모델의 추론 및 학습 방법을 추가하여 성능 및 속도 개선 광주과학기술원 전기전자컴퓨터공학부 신종원 교수 연구팀은 최근 플로우 매칭 (flow matching) 기반의 음성향상 모델의 속도 및 성능을 개선할 수 있는 학습방법 및 추론방법을 개발하였고 국제 음성신호처리 학회인 Interspeech 2025에 논문을 출간하였다. (논문링크: Speech Enhancement based on cascaded two flows … Read more
[논문리뷰] Microphone Array Processing for Distant Speech Recognition: From Close-Talking Microphones to FarField Sensors
Microphone Array Processing for Distant Speech Recognition: From Close-Talking Microphones to FarField Sensors.pdf
[신입생세미나] Chapter 6. Time-domain Methods for Speech Processing
Chapter 6. Time-domain Methods for Speech Processing 220512_신입생세미나_이성규_Ch6_1_Time-domain methods for speech processing 220512_신입생세미나_이성규_Ch6_1_Time-domain methods for speech processing 6.1. Introduction 6.2. Short-time analysis of speech 6.2.1. General framework for short-time analysis 6.2.2. Filtering and sampling in short-time analysis 6.3. Short-time energy and short-time magnitude 6.3.1. Automatic gain control based on short-time energy 6.3.2. Short-time magnitude