https://sapl.gist.ac.kr Speech and Audio Processing Lab. [랩 세미나] 03.27(금) 10:30 ~ ㅁ주제 : Incentivizing Generalization Capability for LLaMA-based Speech Enhancement ㅁ발표자 : 강경묵 [신입생 세미나] 03.26(목) 10:30 ~ ㅁ주제 : Chapter 2.5 Sampling ㅁ발표자 : 김정연]]> Fri, 27 Mar 2026 10:18:25 +0000 [랩 세미나] 03.20(금) 10:30 ~ ㅁ주제 : OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation ㅁ발표자 : 전제우 [신입생 세미나] 03.19(목) 10:30 ~ ㅁ주제 : Chapter 2.4 Fundamentals of Digital Filters ㅁ발표자 : 이현서]]> Thu, 19 Mar 2026 22:34:53 +0000 [랩 세미나] 03.13(금) 10:30 ~ ㅁ주제 : Generative Modeling via Drifting ㅁ발표자 : 유종문 [신입생 세미나] 03.12(목) 10:30 ~ ㅁ주제 : Chapter 2. Review of Fundamentals of Digital Signal Processing (CH 2.4-2.5) ㅁ발표자 : 이현서]]> Thu, 12 Mar 2026 20:51:17 +0000 [랩 세미나] 03.06(금) 10:30 ~ ㅁ주제 : Classifier-guided Gradient Modulation for Enhanced Multimodal Learning ㅁ발표자 : 우현섭 [신입생 세미나] 03.05(목) 15:00 ~ ㅁ주제 : Chapter 2. Review of Fundamentals of Digital Signal Processing (CH 2.1-2.3) ㅁ발표자 : 양예진]]> Fri, 06 Mar 2026 13:48:18 +0000 ParaMETA: Towards Learning Disentangled Paralinguistic Speaking Styles Representations from Speech ㅁ발표자 : 김기혁]]> Fri, 27 Feb 2026 14:09:43 +0000 TF-SkiMNet: Speech Enhancement Based on Inplace Modeling and Skipping Memory in Time-Frequency Domain  ㅁ발표자 : 채종욱]]> Fri, 20 Feb 2026 17:00:37 +0000 DOA or Speaker Embedding: Which is Better for Multi-Microphone Target Speaker Extraction ㅁ발표자 : 손주혜]]> Fri, 20 Feb 2026 16:59:38 +0000 Calibrating Multimodal Learning ㅁ발표자 : 이성규]]> Wed, 11 Feb 2026 09:43:46 +0000 LCMV-based Scan-and-Sum Beamforming for Region Source Extraction ㅁ발표자 : 강경묵]]> Wed, 11 Feb 2026 09:42:56 +0000 CosyVoice:  A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Token ㅁ발표자 : 한상욱]]> Fri, 23 Jan 2026 12:13:45 +0000 Unlocking the Power of Multimodal Learning for Emotion Recognition in Conversation ㅁ발표자 : 우현섭]]> Tue, 20 Jan 2026 10:40:52 +0000 Token Merging: Your ViT But Faster ㅁ발표자 : 김기혁]]> Tue, 13 Jan 2026 10:42:29 +0000 Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder ㅁ발표자 : 채종욱]]> Fri, 26 Dec 2025 09:50:59 +0000 Robust Audio Watermarking Against Manipulation Attacks Based on Deep Learning ㅁ발표자 : 이은균]]> Fri, 19 Dec 2025 17:19:19 +0000 RUMAA: Repeat-Aware Unified Music Audio Analysis for Score-Performance Alignment, Transcription, and Mistake Detection ㅁ발표자 : 전제우]]> Sun, 14 Dec 2025 20:16:54 +0000 Robust Sound Source Tracking Using SRP-PHAT and 3D Convolutional Neural Networks ㅁ발표자 : 강경묵]]> Sun, 07 Dec 2025 15:18:21 +0000 Mutliscale Convolutional Fusion Network for Efficient Monaural Speech Separation ㅁ발표자 : 김현승]]> Tue, 18 Nov 2025 23:05:17 +0000 Defending against Adversarial Audio via Diffusion Model  ㅁ발표자 : 우현섭]]> Tue, 18 Nov 2025 23:03:41 +0000 Scalable Diffusion Models with Transformers ㅁ발표자 : 유종문]]> Tue, 18 Nov 2025 23:02:32 +0000 Tue, 18 Nov 2025 22:57:58 +0000