# Adaptive Knowledge Distillation between Text and Speech Pre-trained Models

arXiv: https://arxiv.org/abs/2303.03600 · HTML: https://mlsanity.com/paper/2303.03600/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 16 of its 22 references that are in the map.
- First posted on arXiv 7 Mar 2023.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [SUPERB: Speech processing Universal PERformance Benchmark](https://mlsanity.com/paper/2105.01051/) (2021)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing](https://mlsanity.com/paper/2110.07205/) (2021)
- [Lite Transformer with Long-Short Range Attention](https://mlsanity.com/paper/2004.11886/) (2020)
- [mSLAM: Massively multilingual joint pre-training for speech and text](https://mlsanity.com/paper/2202.01374/) (2022)
- [SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training](https://mlsanity.com/paper/2110.10329/) (2021)
- [Cross-Modal Discrete Representation Learning](https://mlsanity.com/paper/2106.05438/) (2021)
- [Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understanding](https://mlsanity.com/paper/2011.09044/) (2020)
- [Pretrained Semantic Speech Embeddings for End-to-End Spoken Language Understanding via Cross-Modal Teacher-Student Learning](https://mlsanity.com/paper/2007.01836/) (2020)
- [CALM: Contrastive Aligned Audio-Language Multirate and Multimodal Representations](https://mlsanity.com/paper/2202.03587/) (2022)

## Built on by (most cited first, 3 of 3)

- [CLASP: Contrastive Language-Speech Pretraining for Multilingual Multimodal Information Retrieval](https://mlsanity.com/paper/2412.13071/) (2024)
- [LLM on a Budget: Active Knowledge Distillation for Efficient Classification of Large Text Corpora](https://mlsanity.com/paper/2511.11574/) (2025)
- [Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots](https://mlsanity.com/paper/2607.26567/) (2026)

## Abstract (arXiv)

Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between text and speech has been omitted in literature, which impairs the distillation, we propose the Prior-informed Adaptive knowledge Distillation (PAD) that adaptively leverages text/speech units of variable granularity and prior distributions to achieve better global and local alignments between text and speech pre-trained models. We evaluate on three spoken language understanding benchmarks to show that PAD is more effective in transferring linguistic knowledge than other metric-based distillation approaches.