# Optimizing Neural Speech Codec for Low-Bitrate Compression via Multi-Scale Encoding

arXiv: https://arxiv.org/abs/2410.15749 · HTML: https://mlsanity.com/paper/2410.15749/

## Key facts

- Cited by 1 papers in the map (data through 19 Oct 2026).
- Placed in Vocoders and speech synthesis, one of 11 directions in Speech and audio language models.
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Placed in

- Speech and audio language models / [Vocoders and speech synthesis](https://mlsanity.com/speech/vocoders-and-speech-synthesis/)

## Builds on (most cited first, 19 of 19)

- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [High Fidelity Neural Audio Compression](https://mlsanity.com/paper/2210.13438/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [UTMOS: UTokyo-SaruLab System for VoiceMOS Challenge 2022](https://mlsanity.com/paper/2204.02152/) (2022)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models](https://mlsanity.com/paper/2403.03100/) (2024)
- [CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information](https://mlsanity.com/paper/2006.12013/) (2020)
- [Speak, Read and Prompt: High-Fidelity Text-to-Speech with Minimal Supervision](https://mlsanity.com/paper/2302.03540/) (2023)
- [HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec](https://mlsanity.com/paper/2305.02765/) (2023)
- [AISHELL-3: A Multi-speaker Mandarin TTS Corpus and the Baselines](https://mlsanity.com/paper/2010.11567/) (2020)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [FunCodec: A Fundamental, Reproducible and Integrable Open-source Toolkit for Neural Speech Codec](https://mlsanity.com/paper/2309.07405/) (2023)
- [Hi-Fi Multi-Speaker English TTS Dataset](https://mlsanity.com/paper/2104.01497/) (2021)
- [VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion](https://mlsanity.com/paper/2106.10132/) (2021)
- [Single-Codec: Single-Codebook Speech Codec towards High-Performance Speech Generation](https://mlsanity.com/paper/2406.07422/) (2024)
- [Fewer-token Neural Speech Codec with Time-invariant Codes](https://mlsanity.com/paper/2310.00014/) (2023)
- [Cross-lingual Multi-speaker Text-to-speech Synthesis for Voice Cloning without Using Parallel Corpus for Unseen Speakers](https://mlsanity.com/paper/1911.11601/) (2019)

## Built on by (most cited first, 1 of 1)

- [Analysis of Speaker Verification Performance Trade-offs with Neural Audio Codec Transmission](https://mlsanity.com/paper/2509.02771/) (2025)

## Abstract (arXiv)

Neural speech codecs have demonstrated their ability to compress high-quality speech and audio by converting them into discrete token representations. Most existing methods utilize Residual Vector Quantization (RVQ) to encode speech into multiple layers of discrete codes with uniform time scales. However, this strategy overlooks the differences in information density across various speech features, leading to redundant encoding of sparse information, which limits the performance of these methods at low bitrate. This paper proposes MsCodec, a novel multi-scale neural speech codec that encodes speech into multiple layers of discrete codes, each corresponding to a different time scale. This encourages the model to decouple speech features according to their diverse information densities, consequently enhancing the performance of speech compression. Furthermore, we incorporate mutual information loss to augment the diversity among speech codes across different layers. Experimental results indicate that our proposed method significantly improves codec performance at low bitrate.