AASP-L3.4
Arbitrarily Settable Frame Rate Neural Speech Codec with Content Adaptive Variable Length Segmentation
Yukun Qian, Wenjie Zhang, Xuyi Zhuang, Shiyun Xu, Lianyu Zhou, Mingjiang Wang, Harbin Institute of Technology (Shenzhen), China
Session:
AASP-L3: Neural Speech and Audio Coding Oral
Track:
Audio and Acoustic Signal Processing [AA]
Location:
Room 127+128
Presentation Time:
Wed, 6 May, 10:00 - 10:20
Session Chair:
Jan Skoglund, Google
Session AASP-L3
AASP-L3.1: S-PRESSO: ULTRA LOW BITRATE SOUND EFFECT COMPRESSION WITH DIFFUSION AUTOENCODERS AND OFFLINE QUANTIZATION
Zineb Lahrichi, Gaëtan Hadjeres, Sony AI, France; Gaël Richard, Geoffroy Peeters, LTCI, Télécom Paris, Institut Polytechnique de Paris, France
AASP-L3.2: ACOUSTIC TELEPORTATION VIA DISENTANGLED NEURAL AUDIO CODEC REPRESENTATIONS
Philipp Grundhuber, Mhd Modar Halimeh, Fraunhofer Institute for Integrated Circuits, Germany; Emanuël Habets, International Audio Laboratories Erlangen, Germany
AASP-L3.3: Residual Tokens Enhance Masked Autoencoders for Speech Modeling
Samir Sadok, Stéphane Lathuilière, Xavier Alameda-Pineda, INRIA, France
AASP-L3.4: Arbitrarily Settable Frame Rate Neural Speech Codec with Content Adaptive Variable Length Segmentation
Yukun Qian, Wenjie Zhang, Xuyi Zhuang, Shiyun Xu, Lianyu Zhou, Mingjiang Wang, Harbin Institute of Technology (Shenzhen), China
AASP-L3.5: Lisa: Lightweight Yet Superb Neural Speech Coding
Jiankai Huang, Junteng Zhang, Ming Lu, Xun Cao, Zhan Ma, Nanjing University, China
AASP-L3.6: SWITCHCODEC: ADAPTIVE RESIDUAL-EXPERT SPARSE QUANTIZATION FOR HIGH-FIDELITY NEURAL AUDIO CODING
Xiangbo Wang, Hangzhou dianzi university, China; Wenbin Jiang, Jin Wang, Yubo You, Hangzhou Dianzi University, China; Sheng Fang, Hangzhou dianzi university, China; Fei Wen, Shanghai Jiao Tong University, China
Contacts