# voc2vec: A Foundation Model for Non-Verbal Vocalization

arXiv: https://arxiv.org/abs/2502.16298 · HTML: https://mlsanity.com/paper/2502.16298/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Feb 2025.

## Built on by (most cited first, 5 of 5)

- [Exploring Generative Error Correction for Dysarthric Speech Recognition](https://mlsanity.com/paper/2505.20163/) (2025)
- [MVP: Multi-source Voice Pathology detection](https://mlsanity.com/paper/2505.20050/) (2025)
- [A Concept-based approach to Voice Disorder Detection](https://mlsanity.com/paper/2507.17799/) (2025)
- [Non-Verbal Vocalisations and their Challenges: Emotion, Privacy, Sparseness, and Real Life](https://mlsanity.com/paper/2508.01960/) (2025)
- [Speaker Identity in Non-Verbal Vocalizations: Conditional Distillation and Mixture of Experts Approach](https://mlsanity.com/paper/2606.21215/) (2026)

## Abstract (arXiv)

Speech foundation models have demonstrated exceptional capabilities in speech-related tasks. Nevertheless, these models often struggle with non-verbal audio data, such as vocalizations, baby crying, etc., which are critical for various real-world applications. Audio foundation models well handle non-speech data but also fail to capture the nuanced features of non-verbal human sounds. In this work, we aim to overcome the above shortcoming and propose a novel foundation model, termed voc2vec, specifically designed for non-verbal human data leveraging exclusively open-source non-verbal audio datasets. We employ a collection of 10 datasets covering around 125 hours of non-verbal audio. Experimental results prove that voc2vec is effective in non-verbal vocalization classification, and it outperforms conventional speech and audio foundation models. Moreover, voc2vec consistently outperforms strong baselines, namely OpenSmile and emotion2vec, on six different benchmark datasets. To the best of the authors' knowledge, voc2vec is the first universal representation model for vocalization tasks.