# Linguistic Knowledge Transfer Learning for Speech Enhancement

arXiv: https://arxiv.org/abs/2503.07078 · HTML: https://mlsanity.com/paper/2503.07078/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 92 references that are in the map.
- First posted on arXiv 10 Mar 2025.

## Builds on (most cited first, 30 of 50)

- [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)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding](https://mlsanity.com/paper/2306.02858/) (2023)
- [Language Is Not All You Need: Aligning Perception with Language Models](https://mlsanity.com/paper/2302.14045/) (2023)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [AISHELL-1: An Open-Source Mandarin Speech Corpus and A Speech Recognition Baseline](https://mlsanity.com/paper/1709.05522/) (2017)
- [SEGAN: Speech Enhancement Generative Adversarial Network](https://mlsanity.com/paper/1703.09452/) (2017)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [On decoder-only architecture for speech-to-text and large language model integration](https://mlsanity.com/paper/2307.03917/) (2023)
- [DCCRN: Deep Complex Convolution Recurrent Network for Phase-Aware Speech Enhancement](https://mlsanity.com/paper/2008.00264/) (2020)
- [Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning](https://mlsanity.com/paper/2406.11161/) (2024)
- [StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation](https://mlsanity.com/paper/2212.11851/) (2022)
- [MetricGAN: Generative Adversarial Networks based Black-box Metric Scores Optimization for Speech Enhancement](https://mlsanity.com/paper/1905.04874/) (2019)
- [Speech Enhancement with Score-Based Generative Models in the Complex STFT Domain](https://mlsanity.com/paper/2203.17004/) (2022)
- [Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition](https://mlsanity.com/paper/2310.06434/) (2023)
- [MP-SENet: A Speech Enhancement Model with Parallel Denoising of Magnitude and Phase Spectra](https://mlsanity.com/paper/2305.13686/) (2023)
- [Distilling the Knowledge of BERT for Sequence-to-Sequence ASR](https://mlsanity.com/paper/2008.03822/) (2020)
- [TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain](https://mlsanity.com/paper/2103.09963/) (2021)
- [A Fully Convolutional Neural Network for Speech Enhancement](https://mlsanity.com/paper/1609.07132/) (2016)
- [CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement](https://mlsanity.com/paper/2209.11112/) (2022)
- [Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text Representations](https://mlsanity.com/paper/2303.01664/) (2023)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Boosting Large Language Model for Speech Synthesis: An Empirical Study](https://mlsanity.com/paper/2401.00246/) (2023)
- [Conditional Generative Adversarial Networks for Speech Enhancement and Noise-Robust Speaker Verification](https://mlsanity.com/paper/1709.01703/) (2017)
- [Knowledge Transfer from Large-scale Pretrained Language Models to End-to-end Speech Recognizers](https://mlsanity.com/paper/2202.07894/) (2022)
- [DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement](https://mlsanity.com/paper/2106.15813/) (2021)

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

- [Leveraging Discriminative Latent Representations for Conditioning GAN-Based Speech Enhancement](https://mlsanity.com/paper/2508.20859/) (2025)
- [ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction](https://mlsanity.com/paper/2511.06288/) (2025)
- [Optimal transport meets speech: a tutorial review](https://mlsanity.com/paper/2609.31787/) (2026)

## Abstract (arXiv)

Linguistic knowledge plays a crucial role in spoken language comprehension. It provides essential semantic and syntactic context for speech perception in noisy environments. However, most speech enhancement (SE) methods predominantly rely on acoustic features to learn the mapping relationship between noisy and clean speech, with limited exploration of linguistic integration. While text-informed SE approaches have been investigated, they often require explicit speech-text alignment or externally provided textual data, constraining their practicality in real-world scenarios. Additionally, using text as input poses challenges in aligning linguistic and acoustic representations due to their inherent differences. In this study, we propose the Cross-Modality Knowledge Transfer (CMKT) learning framework, which leverages pre-trained large language models (LLMs) to infuse linguistic knowledge into SE models without requiring text input or LLMs during inference. Furthermore, we introduce a misalignment strategy to improve knowledge transfer. This strategy applies controlled temporal shifts, encouraging the model to learn more robust representations. Experimental evaluations demonstrate that CMKT consistently outperforms baseline models across various SE architectures and LLM embeddings, highlighting its adaptability to different configurations. Additionally, results on Mandarin and English datasets confirm its effectiveness across diverse linguistic conditions, further validating its robustness. Moreover, CMKT remains effective even in scenarios without textual data, underscoring its practicality for real-world applications. By bridging the gap between linguistic and acoustic modalities, CMKT offers a scalable and innovative solution for integrating linguistic knowledge into SE models, leading to substantial improvements in both intelligibility and enhancement performance.