# Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations

arXiv: https://arxiv.org/abs/2407.03495 · HTML: https://mlsanity.com/paper/2407.03495/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 38 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 30 of 33)

- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (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)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Finite Scalar Quantization: VQ-VAE Made Simple](https://mlsanity.com/paper/2309.15505/) (2023)
- [High-Fidelity Audio Compression with Improved RVQGAN](https://mlsanity.com/paper/2306.06546/) (2023)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition](https://mlsanity.com/paper/2305.05084/) (2023)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [TasNet: time-domain audio separation network for real-time, single-channel speech separation](https://mlsanity.com/paper/1711.00541/) (2017)
- [SoundStorm: Efficient Parallel Audio Generation](https://mlsanity.com/paper/2305.09636/) (2023)
- [NEFTune: Noisy Embeddings Improve Instruction Finetuning](https://mlsanity.com/paper/2310.05914/) (2023)
- [SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models](https://mlsanity.com/paper/2308.16692/) (2023)
- [SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Network](https://mlsanity.com/paper/2104.02133/) (2021)
- [ML-SUPERB: Multilingual Speech Universal PERformance Benchmark](https://mlsanity.com/paper/2305.10615/) (2023)
- [LEAF: A Learnable Frontend for Audio Classification](https://mlsanity.com/paper/2101.08596/) (2021)
- [SpeechX: Neural Codec Language Model as a Versatile Speech Transformer](https://mlsanity.com/paper/2308.06873/) (2023)
- [AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec](https://mlsanity.com/paper/2305.16608/) (2023)
- [Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study](https://mlsanity.com/paper/2309.15800/) (2023)
- [Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning](https://mlsanity.com/paper/2305.18108/) (2023)
- [RepCodec: A Speech Representation Codec for Speech Tokenization](https://mlsanity.com/paper/2309.00169/) (2023)

## Built on by (most cited first, 8 of 8)

- [Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs](https://mlsanity.com/paper/2511.16639/) (2025)
- [Analysing the Language of Neural Audio Codecs](https://mlsanity.com/paper/2509.01390/) (2025)
- [Finite Scalar Quantization Enables Redundant and Transmission-Robust Neural Audio Compression at Low Bit-rates](https://mlsanity.com/paper/2509.09550/) (2025)
- [UniVoice: Unifying Autoregressive ASR and Flow-Matching based TTS with Large Language Models](https://mlsanity.com/paper/2510.04593/) (2025)
- [Explainable Disentanglement on Discrete Speech Representations for Noise-Robust ASR](https://mlsanity.com/paper/2510.25150/) (2025)
- [Language-Statistical Analysis of Neural Audio Codec Tokens Across Architectures, Corpora, and Noise Conditions](https://mlsanity.com/paper/2608.31037/) (2026)
- [Robust Residual Finite Scalar Quantization for Neural Compression](https://mlsanity.com/paper/2508.15860/) (2025)
- [MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables](https://mlsanity.com/paper/2605.29859/) (2026)

## Abstract (arXiv)

Discrete speech representations have garnered recent attention for their efficacy in training transformer-based models for various speech-related tasks such as automatic speech recognition (ASR), translation, speaker verification, and joint speech-text foundational models. In this work, we present a comprehensive analysis on building ASR systems with discrete codes. We investigate different methods for codec training such as quantization schemes and time-domain vs spectral feature encodings. We further explore ASR training techniques aimed at enhancing performance, training efficiency, and noise robustness. Drawing upon our findings, we introduce a codec ASR pipeline that outperforms Encodec at similar bit-rate. Remarkably, it also surpasses the state-of-the-art results achieved by strong self-supervised models on the 143 languages ML-SUPERB benchmark despite being smaller in size and pretrained on significantly less data.