# Investigating Neural Audio Codecs for Speech Language Model-Based Speech Generation

arXiv: https://arxiv.org/abs/2409.04016 · HTML: https://mlsanity.com/paper/2409.04016/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Sep 2024.

## Built on by (most cited first, 4 of 4)

- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [Next Tokens Denoising for Speech Synthesis](https://mlsanity.com/paper/2507.22746/) (2025)
- [Do Neural Codecs Generalize? A Controlled Study Across Unseen Languages and Non-Speech Tasks](https://mlsanity.com/paper/2601.12205/) (2026)
- [Investigating Group Relative Policy Optimization for Diffusion Transformer based Text-to-Audio Generation](https://mlsanity.com/paper/2603.01565/) (2026)

## Abstract (arXiv)

Neural audio codec tokens serve as the fundamental building blocks for speech language model (SLM)-based speech generation. However, there is no systematic understanding on how the codec system affects the speech generation performance of the SLM. In this work, we examine codec tokens within SLM framework for speech generation to provide insights for effective codec design. We retrain existing high-performing neural codec models on the same data set and loss functions to compare their performance in a uniform setting. We integrate codec tokens into two SLM systems: masked-based parallel speech generation system and an auto-regressive (AR) plus non-auto-regressive (NAR) model-based system. Our findings indicate that better speech reconstruction in codec systems does not guarantee improved speech generation in SLM. A high-quality codec decoder is crucial for natural speech production in SLM, while speech intelligibility depends more on quantization mechanism.