# Toward Joint Language Modeling for Speech Units and Text

arXiv: https://arxiv.org/abs/2310.08715 · HTML: https://mlsanity.com/paper/2310.08715/

## Key facts

- Cited by 28 papers in the map (data through 14 Oct 2026).
- Builds on 41 of its 47 references that are in the map.
- First posted on arXiv 12 Oct 2023.

## Builds on (most cited first, 30 of 41)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [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)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers](https://mlsanity.com/paper/2301.02111/) (2023)
- [GPT Understands, Too](https://mlsanity.com/paper/2103.10385/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [MLS: A Large-Scale Multilingual Dataset for Speech Research](https://mlsanity.com/paper/2012.03411/) (2020)
- [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](https://mlsanity.com/paper/2101.00390/) (2021)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [Using the Output Embedding to Improve Language Models](https://mlsanity.com/paper/1608.05859/) (2016)
- [Speech Resynthesis from Discrete Disentangled Self-Supervised Representations](https://mlsanity.com/paper/2104.00355/) (2021)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Comparative layer-wise analysis of self-supervised speech models](https://mlsanity.com/paper/2211.03929/) (2022)
- [Direct speech-to-speech translation with discrete units](https://mlsanity.com/paper/2107.05604/) (2021)
- [Scaling Laws for Generative Mixed-Modal Language Models](https://mlsanity.com/paper/2301.03728/) (2023)
- [Textless Speech-to-Speech Translation on Real Data](https://mlsanity.com/paper/2112.08352/) (2021)
- [Text-Free Prosody-Aware Generative Spoken Language Modeling](https://mlsanity.com/paper/2109.03264/) (2021)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [EXPRESSO: A Benchmark and Analysis of Discrete Expressive Speech Resynthesis](https://mlsanity.com/paper/2308.05725/) (2023)

## Built on by (most cited first, 28 of 28)

- [Spirit LM: Interleaved Spoken and Written Language Model](https://mlsanity.com/paper/2402.05755/) (2024)
- [On The Landscape of Spoken Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.08528/) (2025)
- [Recent Advances in Speech Language Models: A Survey](https://mlsanity.com/paper/2410.03751/) (2024)
- [Beyond Turn-Based Interfaces: Synchronous LLMs as Full-Duplex Dialogue Agents](https://mlsanity.com/paper/2409.15594/) (2024)
- [mHuBERT-147: A Compact Multilingual HuBERT Model](https://mlsanity.com/paper/2406.06371/) (2024)
- [Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations](https://mlsanity.com/paper/2402.12786/) (2024)
- [SyllableLM: Learning Coarse Semantic Units for Speech Language Models](https://mlsanity.com/paper/2410.04029/) (2024)
- [Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback](https://mlsanity.com/paper/2411.01834/) (2024)
- [PSLM: Parallel Generation of Text and Speech with LLMs for Low-Latency Spoken Dialogue Systems](https://mlsanity.com/paper/2406.12428/) (2024)
- [DiscreteSLU: A Large Language Model with Self-Supervised Discrete Speech Units for Spoken Language Understanding](https://mlsanity.com/paper/2406.09345/) (2024)
- [On the Evaluation of Speech Foundation Models for Spoken Language Understanding](https://mlsanity.com/paper/2406.10083/) (2024)
- [CogniVoice: Multimodal and Multilingual Fusion Networks for Mild Cognitive Impairment Assessment from Spontaneous Speech](https://mlsanity.com/paper/2407.13660/) (2024)
- [Improving Spoken Language Modeling with Phoneme Classification: A Simple Fine-tuning Approach](https://mlsanity.com/paper/2410.00025/) (2024)
- [From TOWER to SPIRE: Adding the Speech Modality to a Translation-Specialist LLM](https://mlsanity.com/paper/2503.10620/) (2025)
- [Flow-SLM: Joint Learning of Linguistic and Acoustic Information for Spoken Language Modeling](https://mlsanity.com/paper/2508.09350/) (2025)
- [Get Large Language Models Ready to Speak: A Late-fusion Approach for Speech Generation](https://mlsanity.com/paper/2410.20336/) (2024)
- [Speech Recognition Rescoring with Large Speech-Text Foundation Models](https://mlsanity.com/paper/2409.16654/) (2024)
- [Efficient Interleaved Speech Modeling through Knowledge Distillation](https://mlsanity.com/paper/2506.23670/) (2025)
- [Direct Punjabi to English speech translation using discrete units](https://mlsanity.com/paper/2402.15967/) (2024)
- [Compact Speech Translation Models via Discrete Speech Units Pretraining](https://mlsanity.com/paper/2402.19333/) (2024)
- [LoASR-Bench: Evaluating Large Speech Language Models on Low-Resource Automatic Speech Recognition Across Language Families](https://mlsanity.com/paper/2603.20042/) (2026)
- [Lexical Tone is Hard to Quantize: Probing Discrete Speech Units in Mandarin and Yor`ub'a](https://mlsanity.com/paper/2604.07467/) (2026)
- [How Tokenization Limits Phonological Knowledge Representation in Language Models and How to Improve Them](https://mlsanity.com/paper/2604.17105/) (2026)
- [Quantifying the Generation Modality Gap in Speech-Text Language Models](https://mlsanity.com/paper/2609.14743/) (2026)
- [Enhancing Code-switched Text-to-Speech Synthesis Capability in Large Language Models with only Monolingual Corpora](https://mlsanity.com/paper/2409.10969/) (2024)
- [Cross-Lingual Interleaving for Speech Language Models](https://mlsanity.com/paper/2512.01865/) (2025)
- [SPAR-K: Scheduled Periodic Alternating Early Exit for Spoken Language Models](https://mlsanity.com/paper/2603.09215/) (2026)
- [Distilling Text LMs into Speech-to-Speech LMs by Matching Internal Text Predictions](https://mlsanity.com/paper/2610.17461/) (2026)

## Abstract (arXiv)

Speech and text are two major forms of human language. The research community has been focusing on mapping speech to text or vice versa for many years. However, in the field of language modeling, very little effort has been made to model them jointly. In light of this, we explore joint language modeling for speech units and text. Specifically, we compare different speech tokenizers to transform continuous speech signals into discrete units and use different methods to construct mixed speech-text data. We introduce automatic metrics to evaluate how well the joint LM mixes speech and text. We also fine-tune the LM on downstream spoken language understanding (SLU) tasks with different modalities (speech or text) and test its performance to assess the model's learning of shared representations. Our results show that by mixing speech units and text with our proposed mixing techniques, the joint LM improves over a speech-only baseline on SLU tasks and shows zero-shot cross-modal transferability.