# Improving Joint Speech-Text Representations Without Alignment

arXiv: https://arxiv.org/abs/2308.06125 · HTML: https://mlsanity.com/paper/2308.06125/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 20 references that are in the map.
- First posted on arXiv 11 Aug 2023.

## Builds on (most cited first, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [AudioLM: a Language Modeling Approach to Audio Generation](https://mlsanity.com/paper/2209.03143/) (2022)
- [Unifying Vision-and-Language Tasks via Text Generation](https://mlsanity.com/paper/2102.02779/) (2021)
- [Hybrid Autoregressive Transducer (hat)](https://mlsanity.com/paper/2003.07705/) (2020)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [MAESTRO: Matched Speech Text Representations through Modality Matching](https://mlsanity.com/paper/2204.03409/) (2022)
- [A General Multi-Task Learning Framework to Leverage Text Data for Speech to Text Tasks](https://mlsanity.com/paper/2010.11338/) (2020)
- [Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systems](https://mlsanity.com/paper/2010.04284/) (2020)
- [Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder](https://mlsanity.com/paper/2105.00026/) (2021)
- [JOIST: A Joint Speech and Text Streaming Model For ASR](https://mlsanity.com/paper/2210.07353/) (2022)
- [Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems](https://mlsanity.com/paper/2203.00006/) (2022)
- [Multi-Modal Data Augmentation for End-to-End ASR](https://mlsanity.com/paper/1803.10299/) (2018)
- [Learning the joint distribution of two sequences using little or no paired data](https://mlsanity.com/paper/2212.03232/) (2022)

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

- [Text Injection for Neural Contextual Biasing](https://mlsanity.com/paper/2406.02921/) (2024)
- [Efficiently Train ASR Models that Memorize Less and Perform Better with Per-core Clipping](https://mlsanity.com/paper/2406.02004/) (2024)
- [ASTRA: Aligning Speech and Text Representations for Asr without Sampling](https://mlsanity.com/paper/2406.06664/) (2024)
- [Rethinking Speech-LLM Integration for ASR: Effective Joint Speech-Text Training by Interleaving](https://mlsanity.com/paper/2607.01733/) (2026)

## Abstract (arXiv)

The last year has seen astonishing progress in text-prompted image generation premised on the idea of a cross-modal representation space in which the text and image domains are represented jointly. In ASR, this idea has found application as joint speech-text encoders that can scale to the capacities of very large parameter models by being trained on both unpaired speech and text. While these methods show promise, they have required special treatment of the sequence-length mismatch inherent in speech and text, either by up-sampling heuristics or an explicit alignment model. In this work, we offer evidence that joint speech-text encoders naturally achieve consistent representations across modalities by disregarding sequence length, and argue that consistency losses could forgive length differences and simply assume the best alignment. We show that such a loss improves downstream WER in both a large-parameter monolingual and multilingual system.