Cover Image

Why Pre-trained Models Fail: Feature Entanglement in Multi-modal Depression Detection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Xiangyu, Ahmed, Beena, Epps, Julien
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Distinctive Feature Codec: An Adaptive Efficient Speech Representation for Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2025)

Why Your Tokenizer Fails in Information Fusion: A Timing-Aware Pre-Quantization Fusion for Video-Enhanced Audio Tokenization
by: Zhang, Xiangyu, et al.
Published: (2026)

SpeechT-RAG: Reliable Depression Detection in LLMs with Retrieval-Augmented Generation Using Speech Timing Information
by: Zhang, Xiangyu, et al.
Published: (2025)

Rethinking Mamba in Speech Processing by Self-Supervised Models
by: Zhang, Xiangyu, et al.
Published: (2024)

When LLMs Meets Acoustic Landmarks: An Efficient Approach to Integrate Speech into Large Language Models for Depression Detection
by: Zhang, Xiangyu, et al.
Published: (2024)

Zero-Shot Cognitive Impairment Detection from Speech Using AudioLLM
by: Shahin, Mostafa, et al.
Published: (2025)

Auto-Landmark: Acoustic Landmark Dataset and Open-Source Toolkit for Landmark Extraction
by: Zhang, Xiangyu, et al.
Published: (2024)

Mamba in Speech: Towards an Alternative to Self-Attention
by: Zhang, Xiangyu, et al.
Published: (2024)

Short-Segment Speaker Verification with Pre-trained Models and Multi-Resolution Encoder
by: Myoung, Jisoo, et al.
Published: (2025)

Advancing Multi-grained Alignment for Contrastive Language-Audio Pre-training
by: Li, Yiming, et al.
Published: (2024)

CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction
by: Ma, Hao, et al.
Published: (2024)

Towards Fine-Grained and Multi-Granular Contrastive Language-Speech Pre-training
by: Yang, Yifan, et al.
Published: (2026)

An Enhanced Audio Feature Tailored for Anomalous Sound Detection Based on Pre-trained Models
by: Zhong, Guirui, et al.
Published: (2025)

Pre-training Music Classification Models via Music Source Separation
by: Garoufis, Christos, et al.
Published: (2023)

End-to-End Speech Recognition with Pre-trained Masked Language Model
by: Higuchi, Yosuke, et al.
Published: (2024)

ComFeAT: Combination of Neural and Spectral Features for Improved Depression Detection
by: Phukan, Orchid Chetia, et al.
Published: (2024)

Rene: A Pre-trained Multi-modal Architecture for Auscultation of Respiratory Diseases
by: Zhang, Pengfei, et al.
Published: (2024)

Temporal Adaptation of Pre-trained Foundation Models for Music Structure Analysis
by: Zhang, Yixiao, et al.
Published: (2025)

Balancing Speech Understanding and Generation Using Continual Pre-training for Codec-based Speech LLM
by: Shi, Jiatong, et al.
Published: (2025)

Speaker Disentanglement of Speech Pre-trained Model Based on Interpretability
by: Zhu, Xiaoxu, et al.
Published: (2025)

Who is Speaking or Who is Depressed? A Controlled Study of Speaker Leakage in Speech-Based Depression Detection
by: Yeh, Hsiang-Chen, et al.
Published: (2026)

Validating Computational Markers of Depressive Behavior: Cross-Linguistic Speech-Based Depression Detection with Neurophysiological Validation
by: Tao, Fuxiang, et al.
Published: (2026)

Speaker-Conditioned Phrase Break Prediction for Text-to-Speech with Phoneme-Level Pre-trained Language Model
by: Yang, Dong, et al.
Published: (2025)

Target Speech Extraction with Pre-trained Self-supervised Learning Models
by: Peng, Junyi, et al.
Published: (2024)

A Pre-training Framework that Encodes Noise Information for Speech Quality Assessment
by: Sultana, Subrina, et al.
Published: (2024)

Music2Fail: Transfer Music to Failed Recorder Style
by: Leong, Chon In, et al.
Published: (2024)

Post-training for Deepfake Speech Detection
by: Ge, Wanying, et al.
Published: (2025)

Generating Speakers by Prompting Listener Impressions for Pre-trained Multi-Speaker Text-to-Speech Systems
by: Chen, Zhengyang, et al.
Published: (2024)

SA-WavLM: Speaker-Aware Self-Supervised Pre-training for Mixture Speech
by: Lin, Jingru, et al.
Published: (2024)

Automatic Detection of Depression in Speech Using Ensemble Convolutional Neural Networks
by: Vázquez-Romero, Adrián, et al.
Published: (2024)

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)

A Study of Data Selection Strategies for Pre-training Self-Supervised Speech Models
by: Whetten, Ryan, et al.
Published: (2026)

Discrete Token Modeling for Multi-Stem Music Source Separation with Language Models
by: Lyu, Pengbo, et al.
Published: (2026)

Disentangling the Prosody and Semantic Information with Pre-trained Model for In-Context Learning based Zero-Shot Voice Conversion
by: Chen, Zhengyang, et al.
Published: (2024)

PSELDNets: Pre-trained Neural Networks on a Large-scale Synthetic Dataset for Sound Event Localization and Detection
by: Hu, Jinbo, et al.
Published: (2024)

Is MixIT Really Unsuitable for Correlated Sources? Exploring MixIT for Unsupervised Pre-training in Music Source Separation
by: Saijo, Kohei, et al.
Published: (2025)

Text-guided HuBERT: Self-Supervised Speech Pre-training via Generative Adversarial Networks
by: Ma, Duo, et al.
Published: (2024)

SONAR: Self-Distilled Continual Pre-training for Domain Adaptive Audio Representation
by: Zhang, Yizhou, et al.
Published: (2025)

Efficient Speech Enhancement via Embeddings from Pre-trained Generative Audioencoders
by: Sun, Xingwei, et al.
Published: (2025)

Heterogeneity over Homogeneity: Investigating Multilingual Speech Pre-Trained Models for Detecting Audio Deepfake
by: Phukan, Orchid Chetia, et al.
Published: (2024)