Audio Time-Scale Modification with Temporal Compressing Networks
Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；National Cheng Kung University（国立成功大学）；National Sun Yat-sen University（国立中山大学）
We propose a novel approach for time-scale modification of audio signals. Unlike traditional methods that rely on the framing technique or the short-time Fourier transform to preserve the frequency during temporal stretching, our neural network model encodes the raw audio into a high-level latent representation, dubbed Neuralgram, where each vector represents 1024 audio sample points. Due to a sufficient compression ratio, we are able to apply arbitrary spatial interpolation of the Neuralgram to perform temporal stretching. Finally, a learned neural decoder synthesizes the time-scaled audio samples based on the stretched Neuralgram representation. Both the encoder and decoder are trained with latent regression losses and adversarial losses in order to obtain high-fidelity audio samples. Despite its simplicity, our method has comparable performance compared to the existing baselines and opens a new possibility in research into modern time-scale modification. Audio samples can be found at https://tsmnet-mmasia23.github.io
Compressing Quaternion Convolutional Neural Networks for Audio Classification
Centre for Vision, Speech and Signal Processing, University of Surrey, U.K.（英国萨里大学视觉、语音和信号处理中心）；King’s College London, U.K.（伦敦国王学院）；Infosys Centre for AI and CSE Department, Indraprastha Institute of Information Technology (IIIT) Delhi, India（印度德里印度理工学院信息技术学院（IIIT）人工智能中心）
STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；International Digital Economy Academy (IDEA)（国际数字经济学院（IDEA））；Shenzhen Graduate School, Peking University（北京大学深圳研究生院）
What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection
State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）；School of Computer and Information Technology, University of Beijing Jiaotong（北京交通大学计算机与信息技术学院）；Department of Automation, Tsinghua University（清华大学自动化系）；University of Science and Technology of China（中国科学技术大学）
STSM-FiLM: A FiLM-Conditioned Neural Architecture for Time-Scale Modification of Speech
Research Center for Information Technology Innovation, Academia Sinica, Taiwan（资讯科技创新研究中心，中华学术院，台湾）；Institute of Information Science, Academia Sinica, Taiwan（信息科学研究所，中华学术院，台湾）；College of Informatics, National Chengchi University, Taiwan（资讯学院，成实大学，台湾）；Institute of Communications Engineering, National Yang Ming Chiao Tung University, Taiwan（通讯工程研究所，阳明交通大学，台湾）；Dept. of Biomedical Science and Engineering, National Central University, Taoyuan, Taiwan（生物医学科学与工程系，国立中央大学，台湾）
Resampling Filter Design for Multirate Neural Audio Effect Processing
Acoustics and Audio, University of Edinburgh（声学与音频，爱丁堡大学）；Acoustics Lab, Department of Information and Communications Engineering, Aalto University（声学实验室，信息与通信工程系，阿尔托大学）；Scottish Graduate School of Arts and Humanities (SGSAH)（苏格兰艺术与人文研究生学院）
