# MVP: Multi-source Voice Pathology detection

arXiv: https://arxiv.org/abs/2505.20050 · HTML: https://mlsanity.com/paper/2505.20050/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 30 references that are in the map.
- First posted on arXiv 26 May 2025.

## Builds on (most cited first, 12 of 12)

- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [FiLM: Visual Reasoning with a General Conditioning Layer](https://mlsanity.com/paper/1709.07871/) (2017)
- [Gated Multimodal Units for Information Fusion](https://mlsanity.com/paper/1702.01992/) (2017)
- [Benchmarking Representations for Speech, Music, and Acoustic Events](https://mlsanity.com/paper/2405.00934/) (2024)
- [Detecting Dementia from Speech and Transcripts using Transformers](https://mlsanity.com/paper/2110.14769/) (2021)
- [Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions](https://mlsanity.com/paper/2406.16128/) (2024)
- [Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech](https://mlsanity.com/paper/2503.10301/) (2025)
- [Voice Disorder Analysis: a Transformer-based Approach](https://mlsanity.com/paper/2406.14693/) (2024)
- [voc2vec: A Foundation Model for Non-Verbal Vocalization](https://mlsanity.com/paper/2502.16298/) (2025)
- [Exploring ASR-Based Wav2Vec2 for Automated Speech Disorder Assessment: Insights and Analysis](https://mlsanity.com/paper/2410.08250/) (2024)
- [A Voice Disease Detection Method Based on MFCCs and Shallow CNN](https://mlsanity.com/paper/2304.08708/) (2023)

## Built on by (most cited first, 2 of 2)

- [A Concept-based approach to Voice Disorder Detection](https://mlsanity.com/paper/2507.17799/) (2025)
- [SpeechDx: A Multi-Task Benchmark for Clinical Speech AI](https://mlsanity.com/paper/2606.17339/) (2026)

## Abstract (arXiv)

Voice disorders significantly impact patient quality of life, yet non-invasive automated diagnosis remains under-explored due to both the scarcity of pathological voice data, and the variability in recording sources. This work introduces MVP (Multi-source Voice Pathology detection), a novel approach that leverages transformers operating directly on raw voice signals. We explore three fusion strategies to combine sentence reading and sustained vowel recordings: waveform concatenation, intermediate feature fusion, and decision-level combination. Empirical validation across the German, Portuguese, and Italian languages shows that intermediate feature fusion using transformers best captures the complementary characteristics of both recording types. Our approach achieves up to +13% AUC improvement over single-source methods.