Apcodec+: A Spectrum-coding-based High-fidelity And High-compression-rate Neural Audio Codec With Staged Training Paradigm
2024 · Hui-Peng Du, Yang Ai, Rui-Chen Zheng, et al.
Abstract
This paper proposes a novel neural audio codec, named APCodec+, which is an improved version of APCodec. The APCodec+ takes the audio amplitude and phase spectra as the coding object, and employs an adversarial training strategy. Innovatively, we propose a two-stage joint-individual training paradigm for APCodec+. In the joint training stage, the encoder, quantizer, decoder and discriminator are jointly trained with complete spectral loss, quantization loss, and adversarial loss. In the individual training stage, the encoder and quantizer fix their parameters and provide high-quality training data for the decoder and discriminator. The decoder and discriminator are individually trained from scratch without the quantization loss. The purpose of introducing individual training is to reduce the learning difficulty of the decoder, thereby further improving the fidelity of the decoded audio. Experimental results confirm that our proposed APCodec+ at low bitrates achieves comparable performa
Authors
(none)
Tags
Stats
Related papers
- Apcodec: A Neural Audio Codec With Parallel Amplitude And Phase Spectrum Encoding And Decoding (2024)11.58
- Stftcodec: High-fidelity Audio Compression Through Time-frequency Domain Representation (2025)2.26
- Mdctcodec: A Lightweight Mdct-based Neural Audio Codec Towards High Sampling Rate And Low Bitrate Scenarios (2024)8.09
- A Neural Speech Codec For Noise Robust Speech Coding (2023)0.00
- Apnet: An All-frame-level Neural Vocoder Incorporating Direct Prediction Of Amplitude And Phase Spectra (2023)9.59
- Apnet2: High-quality And High-efficiency Neural Vocoder With Direct Prediction Of Amplitude And Phase Spectra (2023)6.34
- Spatialcodec: Neural Spatial Speech Coding (2023)3.69
- Scoredec: A Phase-preserving High-fidelity Audio Codec With A Generalized Score-based Diffusion Post-filter (2024)5.84