ResearchWho?
    • Profile Image
    신종원
    Position Associate Professor
    Current Department 광주과학기술원 전기전자컴퓨터공학부
    프로필
    연구 성과
    논문[42]
    #42. Speech Enhancement Using MLP-Based Architecture With Convolutional Token Mixing Module and Squeeze-and-Excitation Network
    Journal Information 2022.11 · IEEE Access · 10:119283-119289
    Identifier (DOI) https://doi.org/10.1109/access.2022.3221440
    #41. Improved Speech Enhancement Considering Speech PSD Uncertainty
    Journal Information 2022 · IEEE/ACM Transactions on Audio Speech and Language Processing
    Identifier (DOI) https://doi.org/10.1109/TASLP.2022.3180676
    프로시딩[12]
    #12. Multi-Corpus Speech Emotion Recognition for Unseen Corpus Using Corpus-Wise Weights in Classification Loss
    Journal Information 2022.09.19
    Identifier (DOI) https://doi.org/10.21437/interspeech.2022-111
    #11. iDeepMMSE: An improved deep learning approach to MMSE speech and noise power spectrum estimation for speech enhancement
    Journal Information 2022.09.19
    Identifier (DOI) https://doi.org/10.21437/interspeech.2022-964
    발표[36]
    #36. End-to-End 기반 다채널 음성분리를 위한 SI-SNR 손실 함수 변조 연구
    Organization 한국통신학회 추계종합학술발표회
    Date 2021.11
    #35. Wav2vec 특징 기반의 한국어 음성감정인식
    Organization 한국통신학회 추계종합학술발표회
    Date 2021.11
    특허[19]
    #19. SYSTEMS, METHOD, APPARATUS, AND COMPUTER-READABLE MEDIA FOR DECOMPOSITION OF A MULTICHANNEL MUSIC SIGNAL
    Identifier [출원] 13280309
    Patent Country 미국
    #18. METHOD OF ENHANCING SPEECH USING VARIABLE POWER BUDGET
    Identifier [출원] 15/355,678
    Patent Country 미국
    팔로우 추천