# Exploring Speech Recognition, Translation, and Understanding with Discrete Speech Units: A Comparative Study

arXiv: https://arxiv.org/abs/2309.15800 · HTML: https://mlsanity.com/paper/2309.15800/

## Key facts

- Cited by 42 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 46 references that are in the map.
- First posted on arXiv 27 Sep 2023.

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [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)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [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)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio](https://mlsanity.com/paper/2106.06909/) (2021)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [AudioPaLM: A Large Language Model That Can Speak and Listen](https://mlsanity.com/paper/2306.12925/) (2023)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [SLURP: A Spoken Language Understanding Resource Package](https://mlsanity.com/paper/2011.13205/) (2020)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [How2: A Large-scale Dataset for Multimodal Language Understanding](https://mlsanity.com/paper/1811.00347/) (2018)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [SeamlessM4T: Massively Multilingual & Multimodal Machine Translation](https://mlsanity.com/paper/2308.11596/) (2023)
- [E-Branchformer: Branchformer with Enhanced merging for speech recognition](https://mlsanity.com/paper/2210.00077/) (2022)
- [SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition](https://mlsanity.com/paper/2104.02014/) (2021)
- [ML-SUPERB: Multilingual Speech Universal PERformance Benchmark](https://mlsanity.com/paper/2305.10615/) (2023)
- [Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data](https://mlsanity.com/paper/2309.13876/) (2023)
- [Exploration of Efficient End-to-End ASR using Discretized Input from Self-Supervised Learning](https://mlsanity.com/paper/2305.18108/) (2023)
- [CTC Alignments Improve Autoregressive Translation](https://mlsanity.com/paper/2210.05200/) (2022)

## Built on by (most cited first, 30 of 42)

- [Self-Supervised Speech Representations are More Phonetic than Semantic](https://mlsanity.com/paper/2406.08619/) (2024)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Recent Advances in Discrete Speech Tokens: A Review](https://mlsanity.com/paper/2502.06490/) (2025)
- [Scaling Properties of Speech Language Models](https://mlsanity.com/paper/2404.00685/) (2024)
- [DASB - Discrete Audio and Speech Benchmark](https://mlsanity.com/paper/2406.14294/) (2024)
- [How Should We Extract Discrete Audio Tokens from Self-Supervised Models?](https://mlsanity.com/paper/2406.10735/) (2024)
- [Sylber: Syllabic Embedding Representation of Speech from Raw Audio](https://mlsanity.com/paper/2410.07168/) (2024)
- [Leveraging Allophony in Self-Supervised Speech Models for Atypical Pronunciation Assessment](https://mlsanity.com/paper/2502.07029/) (2025)
- [AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation](https://mlsanity.com/paper/2312.02512/) (2023)
- [SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks](https://mlsanity.com/paper/2408.13040/) (2024)
- [DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding](https://mlsanity.com/paper/2406.09345/) (2024)
- [LAST: Language Model Aware Speech Tokenization](https://mlsanity.com/paper/2409.03701/) (2024)
- [Codec-ASR: Training Performant Automatic Speech Recognition Systems with Discrete Speech Representations](https://mlsanity.com/paper/2407.03495/) (2024)
- [From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM](https://mlsanity.com/paper/2503.10620/) (2025)
- [Self-Supervised Speech Models Encode Phonetic Context via Position-dependent Orthogonal Subspaces](https://mlsanity.com/paper/2603.12642/) (2026)
- [TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models](https://mlsanity.com/paper/2311.04589/) (2023)
- [Exploring SSL Discrete Tokens for Multilingual ASR](https://mlsanity.com/paper/2409.08805/) (2024)
- [SLIDE: Integrating Speech Language Model with LLM for Spontaneous Spoken Dialogue Generation](https://mlsanity.com/paper/2501.00805/) (2025)
- [Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition](https://mlsanity.com/paper/2411.06968/) (2024)
- [Layer-wise Minimal Pair Probing Reveals Contextual Grammatical-Conceptual Hierarchy in Speech Representations](https://mlsanity.com/paper/2509.15655/) (2025)
- [Children's Speech Recognition through Discrete Token Enhancement](https://mlsanity.com/paper/2406.13431/) (2024)
- [Segmentation-Variant Codebooks for Preservation of Paralinguistic and Prosodic Information](https://mlsanity.com/paper/2505.15667/) (2025)
- [On-device Streaming Discrete Speech Units](https://mlsanity.com/paper/2506.01845/) (2025)
- [Speech Discrete Tokens or Continuous Features? A Comparative Analysis for Spoken Language Understanding in SpeechLLMs](https://mlsanity.com/paper/2508.17863/) (2025)
- [SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data](https://mlsanity.com/paper/2408.00624/) (2024)
- [Discrete Speech Unit Extraction via Independent Component Analysis](https://mlsanity.com/paper/2501.06562/) (2025)
- [Codec2Vec: Self-Supervised Speech Representation Learning Using Neural Speech Codecs](https://mlsanity.com/paper/2511.16639/) (2025)
- [Text-to-Speech for Unseen Speakers via Low-Complexity Discrete Unit-Based Frame Selection](https://mlsanity.com/paper/2408.17432/) (2024)
- [Exploring SSL Discrete Speech Features for Zipformer-based Contextual ASR](https://mlsanity.com/paper/2409.08797/) (2024)
- [Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?](https://mlsanity.com/paper/2409.09221/) (2024)

## Abstract (arXiv)

Speech signals, typically sampled at rates in the tens of thousands per second, contain redundancies, evoking inefficiencies in sequence modeling. High-dimensional speech features such as spectrograms are often used as the input for the subsequent model. However, they can still be redundant. Recent investigations proposed the use of discrete speech units derived from self-supervised learning representations, which significantly compresses the size of speech data. Applying various methods, such as de-duplication and subword modeling, can further compress the speech sequence length. Hence, training time is significantly reduced while retaining notable performance. In this study, we undertake a comprehensive and systematic exploration into the application of discrete units within end-to-end speech processing models. Experiments on 12 automatic speech recognition, 3 speech translation, and 1 spoken language understanding corpora demonstrate that discrete units achieve reasonably good results in almost all the settings. We intend to release our configurations and trained models to foster future research efforts.