HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec

by   Dongchao Yang, et al.

Audio codec models are widely used in audio communication as a crucial technique for compressing audio into discrete representations. Nowadays, audio codec models are increasingly utilized in generation fields as intermediate representations. For instance, AudioLM is an audio generation model that uses the discrete representation of SoundStream as a training target, while VALL-E employs the Encodec model as an intermediate feature to aid TTS tasks. Despite their usefulness, two challenges persist: (1) training these audio codec models can be difficult due to the lack of publicly available training processes and the need for large-scale data and GPUs; (2) achieving good reconstruction performance requires many codebooks, which increases the burden on generation models. In this study, we propose a group-residual vector quantization (GRVQ) technique and use it to develop a novel \textbf{Hi}gh \textbf{Fi}delity Audio Codec model, HiFi-Codec, which only requires 4 codebooks. We train all the models using publicly available TTS data such as LibriTTS, VCTK, AISHELL, and more, with a total duration of over 1000 hours, using 8 GPUs. Our experimental results show that HiFi-Codec outperforms Encodec in terms of reconstruction performance despite requiring only 4 codebooks. To facilitate research in audio codec and generation, we introduce AcademiCodec, the first open-source audio codec toolkit that offers training codes and pre-trained models for Encodec, SoundStream, and HiFi-Codec. Code and pre-trained model can be found on: \href{https://github.com/yangdongchao/AcademiCodec}{https://github.com/yangdongchao/AcademiCodec}


page 1

page 2

page 3

page 4


iNLTK: Natural Language Toolkit for Indic Languages

We present iNLTK, an open-source NLP library consisting of pre-trained l...

GLM-130B: An Open Bilingual Pre-trained Model

We introduce GLM-130B, a bilingual (English and Chinese) pre-trained lan...

FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec

This paper presents FunCodec, a fundamental neural speech codec toolkit,...

Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio Synthesis Systems?

With the similarity between music and speech synthesis from symbolic inp...

An Open-source Benchmark of Deep Learning Models for Audio-visual Apparent and Self-reported Personality Recognition

Personality is crucial for understanding human internal and external sta...

Improving Perceptual Quality of Drum Transcription with the Expanded Groove MIDI Dataset

Classifier metrics, such as accuracy and F-measure score, often serve as...

AudioFormer: Audio Transformer learns audio feature representations from discrete acoustic codes

We propose a method named AudioFormer,which learns audio feature represe...

Please sign up or login with your details

Forgot password? Click here to reset