BROWSE
Detail
Conference Paper
Neural Spectral Band Generation for Audio Coding
Cited 0 time in 
Share 
Share
- Authors
- Woongjib Choi, Byeong Hyeon Kim, Hyungseob Lim, Inseon Jang, Hong-Goo Kang
- Issue Date
- 2025-08
- Citation
- International Speech Communication Association (INTERSPEECH) 2025, pp.624-628
- Language
- English
- Type
- Conference Paper
- Abstract
- Spectral band replication (SBR) enables bit-efficient coding by generating high-frequency bands from the low-frequency ones. However, it only utilizes coarse spectral features upon a subband-wise signal replication, limiting adaptability to diverse acoustic signals. In this paper, we explore the efficacy of a deep neural network (DNN)-based generative approach for coding the high-frequency bands, which we call neural spectral band generation (n-SBG). Specifically, we propose a DNN-based encoder-decoder structure to extract and quantize the side information related to the high-frequency components and generate the components given both the side information and the decoded core-band signals. The whole coding pipeline is optimized with generative adversarial criteria to enable the generation of perceptually plausible sound. From experiments using AAC as the core codec, we show that the proposed method achieves a better perceptual quality than HE-AAC-v1 with much less side information.
- KSP Keywords
- Acoustic signal, Audio coding, Deep neural network(DNN), Efficient coding, Encoder and Decoder, High frequency(HF), Low frequency, Perceptual Quality, Spectral Band Replication(SBR), frequency band, high-frequency components