neural-audio-codec-survey's Introduction

A Survey on Neural Audio Codec

A preliminary survey on neural audio codec.

(2023/11) Generative De-Quantization for Neural Speech Codec via Latent Diffusion

[paper] [demo] [code] [Submitted to ICASSP 2024]
(2023/09) FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec

[paper] [demo] [code] [Submitted to ICASSP 2024]
(2023/09) RepCodec: A Speech Representation Codec for Speech Tokenization

[paper] [code]
(2023/08) SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models

[paper] [demo] [code] [disentangle semantic token]
(2023/06) DAC: High-Fidelity Audio Compression with Improved RVQGAN

[paper] [demo] [code] [NeurIPS 2023]
(2023/05) AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec

[paper] [demo] [code] [ICASSP 2023]
(2023/05) HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec

[paper] [code]
(2022/10) High Fidelity Neural Audio Compression

[paper] [demo] [code]
(2021/07) SoundStream: An End-to-End Neural Audio Codec

[paper] [demo]

Evaluation

You can refer to the analyses in AudioDecBenchmark [Github], which include evaluations of different neural codecs in the below aspects:

Reconstruction Quality
Speech Synthesis
Speech Comprehension
Deconstruction of various elements within speech, for example, the inforamtion of speakers, timbre, prosody, etc.

Recommend Projects