# Transfer Learning for Speech and Language Processing

arXiv: https://arxiv.org/abs/1511.06066 · HTML: https://mlsanity.com/paper/1511.06066/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 30 of 35)

- [T-Miner: A Generative Approach to Defend Against Trojan Attacks on DNN-based Text Classification](https://mlsanity.com/paper/2103.04264/) (2021)
- [Middle-Layer Representation Alignment for Cross-Lingual Transfer in Fine-Tuned LLMs](https://mlsanity.com/paper/2502.14830/) (2025)
- [Refining Language Models with Compositional Explanations](https://mlsanity.com/paper/2103.10415/) (2021)
- [Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition](https://mlsanity.com/paper/2110.04934/) (2021)
- [Unsupervised Noise Adaptive Speech Enhancement by Discriminator-Constrained Optimal Transport](https://mlsanity.com/paper/2111.06316/) (2021)
- [Speech Resources in the Tamasheq Language](https://mlsanity.com/paper/2201.05051/) (2022)
- [Magic dust for cross-lingual adaptation of monolingual wav2vec-2.0](https://mlsanity.com/paper/2110.03560/) (2021)
- [Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understanding](https://mlsanity.com/paper/2106.15065/) (2021)
- [Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation](https://mlsanity.com/paper/2407.11052/) (2024)
- [Bilateral Personalized Dialogue Generation with Contrastive Learning](https://mlsanity.com/paper/2106.07857/) (2021)
- [Weighted Cross-entropy for Low-Resource Languages in Multilingual Speech Recognition](https://mlsanity.com/paper/2409.16954/) (2024)
- [Generalization in birdsong classification: impact of transfer learning methods and dataset characteristics](https://mlsanity.com/paper/2409.15383/) (2024)
- [Whisper-LM: Improving ASR Models with Language Models for Low-Resource Languages](https://mlsanity.com/paper/2503.23542/) (2025)
- [GearNet: Stepwise Dual Learning for Weakly Supervised Domain Adaptation](https://mlsanity.com/paper/2201.06001/) (2022)
- [Baby Physical Safety Monitoring in Smart Home Using Action Recognition System](https://mlsanity.com/paper/2210.12527/) (2022)
- [AfroDigits: A Community-Driven Spoken Digit Dataset for African Languages](https://mlsanity.com/paper/2303.12582/) (2023)
- [Improving Automatic Speech Recognition for Non-Native English with Transfer Learning and Language Model Decoding](https://mlsanity.com/paper/2202.05209/) (2022)
- [Pretrained audio neural networks for Speech emotion recognition in Portuguese](https://mlsanity.com/paper/2210.14716/) (2022)
- [Neuroplasticity in Artificial Intelligence -- An Overview and Inspirations on Drop In & Out Learning](https://mlsanity.com/paper/2503.21419/) (2025)
- [Humans overrely on overconfident language models, across languages](https://mlsanity.com/paper/2507.06306/) (2025)
- [Bayesian Transfer Learning: An Overview of Probabilistic Graphical Models for Transfer Learning](https://mlsanity.com/paper/2109.13233/) (2021)
- [Flowchase: a Mobile Application for Pronunciation Training](https://mlsanity.com/paper/2307.02051/) (2023)
- [Spatial HuBERT: Self-supervised Spatial Speech Representation Learning for a Single Talker from Multi-channel Audio](https://mlsanity.com/paper/2310.10922/) (2023)
- [Cross-lingual Offensive Language Detection: A Systematic Review of Datasets, Transfer Approaches and Challenges](https://mlsanity.com/paper/2401.09244/) (2024)
- [NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling](https://mlsanity.com/paper/2206.09058/) (2022)
- [Cross-Corpus Multilingual Speech Emotion Recognition: Amharic vs. Other Languages](https://mlsanity.com/paper/2307.10814/) (2023)
- [MUST&P-SRL: Multi-lingual and Unified Syllabification in Text and Phonetic Domains for Speech Representation Learning](https://mlsanity.com/paper/2310.11541/) (2023)
- [Automatic Speech Recognition Advancements for Indigenous Languages of the Americas](https://mlsanity.com/paper/2404.08368/) (2024)
- [Incorporating Lexical and Syntactic Knowledge for Unsupervised Cross-Lingual Transfer](https://mlsanity.com/paper/2404.16627/) (2024)
- [Effective Noise-aware Data Simulation for Domain-adaptive Speech Enhancement Leveraging Dynamic Stochastic Perturbation](https://mlsanity.com/paper/2409.01545/) (2024)

## Abstract (arXiv)

Transfer learning is a vital technique that generalizes models trained for one setting or task to other settings or tasks. For example in speech recognition, an acoustic model trained for one language can be used to recognize speech in another language, with little or no re-training data. Transfer learning is closely related to multi-task learning (cross-lingual vs. multilingual), and is traditionally studied in the name of `model adaptation'. Recent advance in deep learning shows that transfer learning becomes much easier and more effective with high-level abstract features learned by deep models, and the `transfer' can be conducted not only between data distributions and data types, but also between model structures (e.g., shallow nets and deep nets) or even model types (e.g., Bayesian models and neural models). This review paper summarizes some recent prominent research towards this direction, particularly for speech and language processing. We also report some results from our group and highlight the potential of this very interesting research field.