# CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations

arXiv: https://arxiv.org/abs/2109.00181 · HTML: https://mlsanity.com/paper/2109.00181/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 47 references that are in the map.
- First posted on arXiv 1 Sep 2021.

## Builds on (most cited first, 30 of 35)

- [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)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [A large annotated corpus for learning natural language inference](https://mlsanity.com/paper/1508.05326/) (2015)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [RACE: Large-scale ReAding Comprehension Dataset From Examinations](https://mlsanity.com/paper/1704.04683/) (2017)
- [Distributed Representations of Sentences and Documents](https://mlsanity.com/paper/1405.4053/) (2014)
- [Multimodal Transformer for Unaligned Multimodal Language Sequences](https://mlsanity.com/paper/1906.00295/) (2019)
- [From Recognition to Cognition: Visual Commonsense Reasoning](https://mlsanity.com/paper/1811.10830/) (2018)
- [Unicoder-VL: A Universal Encoder for Vision and Language by Cross-modal Pre-training](https://mlsanity.com/paper/1908.06066/) (2019)
- [Tensor Fusion Network for Multimodal Sentiment Analysis](https://mlsanity.com/paper/1707.07250/) (2017)
- [vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations](https://mlsanity.com/paper/1910.05453/) (2019)
- [Generalized End-to-End Loss for Speaker Verification](https://mlsanity.com/paper/1710.10467/) (2017)
- [Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders](https://mlsanity.com/paper/1910.12638/) (2019)
- [TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech](https://mlsanity.com/paper/2007.06028/) (2020)
- [Multi-attention Recurrent Network for Human Communication Comprehension](https://mlsanity.com/paper/1802.00923/) (2018)
- [Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation](https://mlsanity.com/paper/2005.08575/) (2020)
- [Multimodal Speech Emotion Recognition Using Audio and Text](https://mlsanity.com/paper/1810.04635/) (2018)
- [RawNet: Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification](https://mlsanity.com/paper/1904.08104/) (2019)
- [Improving Transformer-based Speech Recognition Using Unsupervised Pre-training](https://mlsanity.com/paper/1910.09932/) (2019)

## Built on by (most cited first, 9 of 9)

- [Implicit Warping for Animation with Image Sets](https://mlsanity.com/paper/2210.01794/) (2022)
- [ChatGPT for Shaping the Future of Dentistry: The Potential of Multi-Modal Large Language Model](https://mlsanity.com/paper/2304.03086/) (2023)
- [Putting GPT-4o to the Sword: A Comprehensive Evaluation of Language, Vision, Speech, and Multimodal Proficiency](https://mlsanity.com/paper/2407.09519/) (2024)
- [Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment](https://mlsanity.com/paper/2305.11579/) (2023)
- [FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion](https://mlsanity.com/paper/2506.01111/) (2025)
- [Self-Supervised Audio-and-Text Pre-training with Extremely Low-Resource Parallel Data](https://mlsanity.com/paper/2204.04645/) (2022)
- [From Text to Talk: Audio-Language Model Needs Non-Autoregressive Joint Training](https://mlsanity.com/paper/2509.20072/) (2025)
- [Training Vision-Language Models with Less Bimodal Supervision](https://mlsanity.com/paper/2211.00262/) (2022)
- [DiVR: incorporating context from diverse VR scenes for human trajectory prediction](https://mlsanity.com/paper/2411.08409/) (2024)

## Abstract (arXiv)

Existing audio-language task-specific predictive approaches focus on building complicated late-fusion mechanisms. However, these models are facing challenges of overfitting with limited labels and low model generalization abilities. In this paper, we present a Cross-modal Transformer for Audio-and-Language, i.e., CTAL, which aims to learn the intra-modality and inter-modality connections between audio and language through two proxy tasks on a large amount of audio-and-language pairs: masked language modeling and masked cross-modal acoustic modeling. After fine-tuning our pre-trained model on multiple downstream audio-and-language tasks, we observe significant improvements across various tasks, such as, emotion classification, sentiment analysis, and speaker verification. On this basis, we further propose a specially-designed fusion mechanism that can be used in fine-tuning phase, which allows our pre-trained model to achieve better performance. Lastly, we demonstrate detailed ablation studies to prove that both our novel cross-modality fusion component and audio-language pre-training methods significantly contribute to the promising results.