Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models

Malo Maisonneuve; Corinne Fredouille; Muriel Lalain; Alain Ghio; Virginie Woisard

Home/Archive/arXiv

arXiv · 2406.07576

Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models

Malo Maisonneuve·Corinne Fredouille·Muriel Lalain·Alain Ghio·Virginie Woisard

View original source ↗Read source document ↗Export metadata ↓

Abstract

Head and Neck Cancers (HNC) significantly impact patients' ability to speak, affecting their quality of life. Commonly used metrics for assessing pathological speech are subjective, prompting the need for automated and unbiased evaluation methods. This study proposes a self-supervised Wav2Vec2-based model for phone classification with HNC patients, to enhance accuracy and improve the discrimination of phonetic features for subsequent interpretability purpose. The impact of pre-training datasets, model size, and fine-tuning datasets and parameters are explored. Evaluation on diverse corpora reveals the effectiveness of the Wav2Vec2 architecture, outperforming a CNN-based approach, used in previous work. Correlation with perceptual measures also affirms the model relevance for impaired speech analysis. This work paves the way for better understanding of pathological speech with interpretable approaches for clinicians, by leveraging complex self-learnt speech representations.

Explore related subjects

eess.AS cs.LG cs.SD

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Malo Maisonneuve, Corinne Fredouille, Muriel Lalain, Alain Ghio, Virginie Woisard. 2024-06-07. Towards objective and interpretable speech disorder assessment: a comparative analysis of CNN and transformer-based models. https://arxiv.org/abs/2406.07576

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Revisiting Lexicon Evaluation in Unsupervised Word Discovery

Building a lexicon from discovered word-like units is a central goal in zero-resource speech processing. But do our evaluations provide a trustworthy indication of lexicon quality? A common metric, normalized edit distance, averages the phoneme edit distances between discovered units in each cluster. We show that this metric has an inherent bias toward the quality of large clusters, inhibiting fair evaluation. Moreover, it ignores how well true classes are distributed across clusters. Based on established theory in clustering literature, we propose two metrics that address these shortcomings: a modified metric that weighs cluster size when assessing within-cluster consistency, and an inverse metric that assesses how true words are spread across clusters. Through experiments on synthetic and real-world lexicons, we demonstrate that combined, these metrics are: (1) more closely correlated with how similar a lexicon is to the ground-truth distribution, and (2) more robust to biases that skew lexicon evaluations.

eess.AS↗

arXiv2026

AURA: Uncertainty-Routed Activation Editing for Acoustic Grounding in Speech Foundation Models

Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs contain no speech, weak acoustic evidence, or unreliable transcription. We propose AURA: Activation-editing with Uncertainty-Routed Adaptation, an ultra-efficient representation-editing method that freezes the pretrained model and applies sparse scale-and-shift edits to decoder cross-attention heads. AURA dynamically routes edits using cross-attention uncertainty features that capture over-concentration, diffuse attention, and abrupt frame shifts. We evaluate AURA on four datasets spanning non-speech hallucination and speech grounding stressors, including imperfect-label child speech, imperfect-label adult speech, and disfluent speech. On non-speech audio, AURA reduces hallucination rate from 89.18% to 1.94% without prior hallucination-head identification. On imperfect-label corpora, AURA approaches LoRA WER while using roughly 500x fewer trainable parameters. Sensitivity analysis and qualitative cross-attention examples are consistent with AURA's uncertainty-routed editing behavior, supporting dynamic activation editing as a practical path for grounding AED speech models.

eess.AS↗

arXiv2026

The design of an optomechanical microphone using a photonic waveguide interferometer

We present an optomechanical microphone based on a diaphragm-integrated photonic waveguide Mach-Zehnder interferometer. Acoustic pressure deforms the MEMS diaphragm, inducing strain in the sensing waveguide and changing its optical path length. We analytically evaluate the optical and mechanical transduction mechanisms and key figures of merit, including signal-to-noise ratio, dynamic range, acoustic overload pressure, and minimum detectable pressure. Two design cases are considered: a MEMS microphone and a measurement microphone. The results indicate competitive performance but no substantial overall advantage over state-of-the-art microphones in conventional applications. The architecture may nevertheless offer advantages for high-temperature and other harsh-environment sensing applications.

eess.AS↗