# Low Frame-rate Speech Codec: a Codec Designed for Fast High-quality Speech LLM Training and Inference

arXiv: https://arxiv.org/abs/2409.12117 · HTML: https://mlsanity.com/paper/2409.12117/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 40 references that are in the map.
- First posted on arXiv 18 Sep 2024.

## Builds on (most cited first, 30 of 32)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [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)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Simple and Controllable Music Generation](https://mlsanity.com/paper/2306.05284/) (2023)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model](https://mlsanity.com/paper/2406.04904/) (2024)
- [StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models](https://mlsanity.com/paper/2306.07691/) (2023)
- [WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling](https://mlsanity.com/paper/2408.16532/) (2024)
- [HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec](https://mlsanity.com/paper/2305.02765/) (2023)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [Hi-Fi Multi-Speaker English TTS Dataset](https://mlsanity.com/paper/2104.01497/) (2021)
- [TorchAudio-Squim: Reference-less Speech Quality and Intelligibility measures in TorchAudio](https://mlsanity.com/paper/2304.01448/) (2023)
- [Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder](https://mlsanity.com/paper/1910.06464/) (2019)
- [End-to-End Optimized Speech Coding with Deep Neural Networks](https://mlsanity.com/paper/1710.09064/) (2017)
- [Fewer-token Neural Speech Codec with Time-invariant Codes](https://mlsanity.com/paper/2310.00014/) (2023)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Textless Direct Speech-to-Speech Translation with Discrete Speech Representation](https://mlsanity.com/paper/2211.00115/) (2022)
- [Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction](https://mlsanity.com/paper/2401.06387/) (2024)
- [APCodec: A Neural Audio Codec with Parallel Amplitude and Phase Spectrum Encoding and Decoding](https://mlsanity.com/paper/2402.10533/) (2024)
- [Joint Pre-Training with Speech and Bilingual Text for Direct Speech to Speech Translation](https://mlsanity.com/paper/2210.17027/) (2022)

## Built on by (most cited first, 11 of 11)

- [OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM](https://mlsanity.com/paper/2510.15870/) (2025)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Koel-TTS: Enhancing LLM based Speech Generation with Preference Alignment and Classifier Free Guidance](https://mlsanity.com/paper/2502.05236/) (2025)
- [FASTer: Toward Efficient Autoregressive Vision Language Action Modeling via Neural Action Tokenization](https://mlsanity.com/paper/2512.04952/) (2025)
- [NanoCodec: Towards High-Quality Ultra Fast Speech LLM Inference](https://mlsanity.com/paper/2508.05835/) (2025)
- [Chronological Thinking in Full-Duplex Spoken Dialogue Language Models](https://mlsanity.com/paper/2510.05150/) (2025)
- [Discrete Tokenization for Multimodal LLMs: A Comprehensive Survey](https://mlsanity.com/paper/2507.22920/) (2025)
- [Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate](https://mlsanity.com/paper/2505.16845/) (2025)
- [CrossAccent-TTS: Cross-Lingual Accent-Intensity Controllable Text-to-Speech via Disentangled Speaker and Accent Representations](https://mlsanity.com/paper/2606.25403/) (2026)
- [S-PRESSO: Ultra Low Bitrate Sound Effect Compression With Diffusion Autoencoders And Offline Quantization](https://mlsanity.com/paper/2602.15082/) (2026)
- [Q-SPT: Learnable Query-Based Compression for Low-Frame-Rate Speech Tokenization](https://mlsanity.com/paper/2610.01492/) (2026)

## Abstract (arXiv)

Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modeling techniques to audio data. However, audio codecs often operate at high frame rates, resulting in slow training and inference, especially for autoregressive models. To address this challenge, we present the Low Frame-rate Speech Codec (LFSC): a neural audio codec that leverages finite scalar quantization and adversarial training with large speech language models to achieve high-quality audio compression with a 1.89 kbps bitrate and 21.5 frames per second. We demonstrate that our novel codec can make the inference of LLM-based text-to-speech models around three times faster while improving intelligibility and producing quality comparable to previous models.