# Towards Robust Assessment of Pathological Voices via Combined Low-Level Descriptors and Foundation Model Representations

arXiv: https://arxiv.org/abs/2505.21356 · HTML: https://mlsanity.com/paper/2505.21356/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 50 references that are in the map.
- First posted on arXiv 27 May 2025.

## Builds on (most cited first, 18 of 18)

- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [Deep Learning-based Non-Intrusive Multi-Objective Speech Assessment Model with Cross-Domain Features](https://mlsanity.com/paper/2111.02363/) (2021)
- [Boosting Self-Supervised Embeddings for Speech Enhancement](https://mlsanity.com/paper/2204.03339/) (2022)
- [Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load](https://mlsanity.com/paper/2203.16637/) (2022)
- [Voice Disorder Analysis: a Transformer-based Approach](https://mlsanity.com/paper/2406.14693/) (2024)
- [Continuous Speech for Improved Learning Pathological Voice Disorders](https://mlsanity.com/paper/2202.10777/) (2022)
- [Whisper-SV: Adapting Whisper for Low-data-resource Speaker Verification](https://mlsanity.com/paper/2407.10048/) (2024)
- [Robust Vocal Quality Feature Embeddings for Dysphonic Voice Detection](https://mlsanity.com/paper/2211.09858/) (2022)
- [HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing Aids](https://mlsanity.com/paper/2401.01145/) (2024)
- [Perceptually inspired weighted MSE optimization using irregularity-aware graph Fourier transform](https://mlsanity.com/paper/2002.08558/) (2020)
- [Predicting Heart Activity from Speech using Data-driven and Knowledge-based features](https://mlsanity.com/paper/2406.06341/) (2024)
- [Toward Real-World Voice Disorder Classification](https://mlsanity.com/paper/2112.02538/) (2021)
- [Multi-objective Non-intrusive Hearing-aid Speech Assessment Model](https://mlsanity.com/paper/2311.08878/) (2023)
- [Lightly Weighted Automatic Audio Parameter Extraction for the Quality Assessment of Consensus Auditory-Perceptual Evaluation of Voice](https://mlsanity.com/paper/2311.15582/) (2023)

## Built on by (most cited first, 1 of 1)

- [QAMRO: Quality-aware Adaptive Margin Ranking Optimization for Human-aligned Assessment of Audio Generation Systems](https://mlsanity.com/paper/2508.08957/) (2025)

## Abstract (arXiv)

Perceptual voice quality assessment plays a vital role in diagnosing and monitoring voice disorders. Traditional methods, such as the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) and the Grade, Roughness, Breathiness, Asthenia, and Strain (GRBAS) scales, rely on expert raters and are prone to inter-rater variability, emphasizing the need for objective solutions. This study introduces the Voice Quality Assessment Network (VOQANet), a deep learning framework that employs an attention mechanism and Speech Foundation Model (SFM) embeddings to extract high-level features. To further enhance performance, we propose VOQANet+, which integrates self-supervised SFM embeddings with low-level acoustic descriptors-namely jitter, shimmer, and harmonics-to-noise ratio (HNR). Unlike previous approaches that focus solely on vowel-based phonation (PVQD-A), our models are evaluated on both vowel-level and sentence-level speech (PVQD-S) to assess generalizability. Experimental results demonstrate that sentence-based inputs yield higher accuracy, particularly at the patient level. Overall, VOQANet consistently outperforms baseline models in terms of root mean squared error (RMSE) and Pearson correlation coefficient across CAPE-V and GRBAS dimensions, with VOQANet+ achieving even greater performance gains. Additionally, VOQANet+ maintains consistent performance under noisy conditions, suggesting enhanced robustness for real-world and telehealth applications. This work highlights the value of combining SFM embeddings with low-level features for accurate and robust pathological voice assessment.