Cover Image

From Black Box to Biomarker: Sparse Autoencoders for Interpreting Speech Models of Parkinson's Disease

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Plantinga, Peter, Chen, Jen-Kai, Sattari, Roozbeh, Ravanelli, Mirco, Klein, Denise
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Does Language Matter for Early Detection of Parkinson's Disease from Speech?
by: Plantinga, Peter, et al.
Published: (2025)

Comparison of Speech Tasks in Human Expert and Machine Detection of Parkinson's Disease
by: Plantinga, Peter, et al.
Published: (2025)

Listen First, Then Answer: Timestamp-Grounded Speech Reasoning
by: Jeong, Jihoon, et al.
Published: (2026)

LL-SDR: Low-Latency Speech enhancement through Discrete Representations
by: Li, Jingyi, et al.
Published: (2026)

Autoregressive Speech Enhancement via Acoustic Tokens
by: Della Libera, Luca, et al.
Published: (2025)

Investigating the Effectiveness of Explainability Methods in Parkinson's Detection from Speech
by: Mancini, Eleonora, et al.
Published: (2024)

Focal Modulation Networks for Interpretable Sound Classification
by: Della Libera, Luca, et al.
Published: (2024)

Parameter-Efficient Transfer Learning of Audio Spectrogram Transformers
by: Cappellazzo, Umberto, et al.
Published: (2023)

What Are They Doing? Joint Audio-Speech Co-Reasoning
by: Wang, Yingzhi, et al.
Published: (2024)

ALAS: Measuring Latent Speech-Text Alignment For Spoken Language Understanding In Multimodal LLMs
by: Mousavi, Pooneh, et al.
Published: (2025)

Investigating Faithfulness in Large Audio Language Models
by: Mousavi, Pooneh, et al.
Published: (2025)

FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation
by: Della Libera, Luca, et al.
Published: (2025)

Phoneme Discretized Saliency Maps for Explainable Detection of AI-Generated Voice
by: Gupta, Shubham, et al.
Published: (2024)

Speech Self-Supervised Representations Benchmarking: a Case for Larger Probing Heads
by: Zaiem, Salah, et al.
Published: (2023)

Listenable Maps for Audio Classifiers
by: Paissan, Francesco, et al.
Published: (2024)

Exploiting Foundation Models and Speech Enhancement for Parkinson's Disease Detection from Speech in Real-World Operative Conditions
by: La Quatra, Moreno, et al.
Published: (2024)

ProGRes: Prompted Generative Rescoring on ASR n-Best
by: Tur, Ada Defne, et al.
Published: (2024)

Speech as a Biomarker for Disease Detection
by: Botelho, Catarina, et al.
Published: (2024)

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks
by: Della Libera, Luca, et al.
Published: (2025)

SKILL: Similarity-aware Knowledge distILLation for Speech Self-Supervised Learning
by: Zampierin, Luca, et al.
Published: (2024)

DASB - Discrete Audio and Speech Benchmark
by: Mousavi, Pooneh, et al.
Published: (2024)

Towards a Generalizable Speech Marker for Parkinson's Disease Diagnosis
by: Siniukov, Maksim, et al.
Published: (2025)

Cross-Lingual Multi-Granularity Framework for Interpretable Parkinson's Disease Diagnosis from Speech
by: Tougui, Ilias, et al.
Published: (2025)

Listenable Maps for Zero-Shot Audio Classifiers
by: Paissan, Francesco, et al.
Published: (2024)

Complex Recurrent Variational Autoencoder with Application to Speech Enhancement
by: Xie, Yuying, et al.
Published: (2022)

Evaluating Parkinson's Disease Detection in Anonymized Speech: A Performance and Acoustic Analysis
by: Franzreb, Carlos, et al.
Published: (2026)

Bilingual Dual-Head Deep Model for Parkinson's Disease Detection from Speech
by: La Quatra, Moreno, et al.
Published: (2025)

Speech-Omni-Lite: Portable Speech Interfaces for Vision-Language Models
by: Tao, Dehua, et al.
Published: (2026)

Linguistic Changes in Spontaneous Speech for Detecting Parkinsons Disease Using Large Language Models
by: Crawford, Jonathan
Published: (2024)

On the Relevance of Clinical Assessment Tasks for the Automatic Detection of Parkinson's Disease Medication State from Speech
by: Gimeno-Gómez, David, et al.
Published: (2025)

LiSTEN: Learning Soft Token Embeddings for Neural Audio LLMs
by: Mousavi, Pooneh, et al.
Published: (2025)

Audio Prototypical Network For Controllable Music Recommendation
by: Öncel, Fırat, et al.
Published: (2025)

LMAC-TD: Producing Time Domain Explanations for Audio Classifiers
by: Mancini, Eleonora, et al.
Published: (2024)

Variational Autoencoder for Personalized Pathological Speech Enhancement
by: Hou, Mingchi, et al.
Published: (2025)

Physics-Informed Neural Network for Volumetric Sound field Reconstruction of Speech Signals
by: Olivieri, Marco, et al.
Published: (2024)

Physics-Informed Neural Network-Driven Sparse Field Discretization Method for Near-Field Acoustic Holography
by: Luan, Xinmeng, et al.
Published: (2025)

Toward Faithful Explanations in Acoustic Anomaly Detection
by: Elrashid, Maab, et al.
Published: (2026)

Towards Unsupervised Speaker Diarization System for Multilingual Telephone Calls Using Pre-trained Whisper Model and Mixture of Sparse Autoencoders
by: Lam, Phat, et al.
Published: (2024)

Rethinking Flow and Diffusion Bridge Models for Speech Enhancement
by: Wang, Dahan, et al.
Published: (2026)

Interpreting the Role of Visemes in Audio-Visual Speech Recognition
by: Papadopoulos, Aristeidis, et al.
Published: (2025)