Cover Image

SGPA: Spectrogram-Guided Phonetic Alignment for Feasible Shapley Value Explanations in Multimodal Large Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pozorski, Paweł, Muszyński, Jakub, Ganzha, Maria
Format:	Preprint
Published:	2026
Subjects:	Sound Audio and Speech Processing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Vision Language Models Are Few-Shot Audio Spectrogram Classifiers
by: Dixit, Satvik, et al.
Published: (2024)

A Practical Guide to Spectrogram Analysis for Audio Signal Processing
by: Khodzhaev, Zulfidin
Published: (2024)

ASGIR: Audio Spectrogram Transformer Guided Classification And Information Retrieval For Birds
by: Chaudhuri, Yashwardhan, et al.
Published: (2024)

ASM: Audio Spectrogram Mixer
by: Ji, Qingfeng, et al.
Published: (2024)

Towards Accurate Phonetic Error Detection Through Phoneme Similarity Modeling
by: Zhou, Xuanru, et al.
Published: (2025)

High-Fidelity Neural Phonetic Posteriorgrams
by: Churchwell, Cameron, et al.
Published: (2024)

FAST: Fast Audio Spectrogram Transformer
by: Naman, Anugunj, et al.
Published: (2025)

PhiNet: Speaker Verification with Phonetic Interpretability
by: Ma, Yi, et al.
Published: (2026)

Phonetic Richness for Improved Automatic Speaker Verification
by: Klein, Nicholas, et al.
Published: (2024)

Multimodal Input Aids a Bayesian Model of Phonetic Learning
by: Zhi, Sophia, et al.
Published: (2024)

Phonetic Enhanced Language Modeling for Text-to-Speech Synthesis
by: Zhou, Kun, et al.
Published: (2024)

Evaluating CNN with Stacked Feature Representations and Audio Spectrogram Transformer Models for Sound Classification
by: Dehaghania, Parinaz Binandeh, et al.
Published: (2026)

Phonetic Segmentation of the UCLA Phonetics Lab Archive
by: Chodroff, Eleanor, et al.
Published: (2024)

Mel-Spectrogram Inversion via Alternating Direction Method of Multipliers
by: Masuyama, Yoshiki, et al.
Published: (2025)

Comparison Performance of Spectrogram and Scalogram as Input of Acoustic Recognition Task
by: Phan, Dang Thoai
Published: (2024)

Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment
by: Gogoi, Parismita, et al.
Published: (2025)

Adapter Incremental Continual Learning of Efficient Audio Spectrogram Transformers
by: Selvaraj, Nithish Muthuchamy, et al.
Published: (2023)

SpecMaskGIT: Masked Generative Modeling of Audio Spectrograms for Efficient Audio Synthesis and Beyond
by: Comunità, Marco, et al.
Published: (2024)

ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
by: Jiang, Xiao-Hang, et al.
Published: (2024)

Quantifying and Reducing Speaker Heterogeneity within the Common Voice Corpus for Phonetic Analysis
by: Zhang, Miao, et al.
Published: (2025)

Enhancing Child Vocalization Classification with Phonetically-Tuned Embeddings for Assisting Autism Diagnosis
by: Li, Jialu, et al.
Published: (2023)

Distilling Spectrograms into Tokens: Fast and Lightweight Bioacoustic Classification for BirdCLEF+ 2025
by: Miyaguchi, Anthony, et al.
Published: (2025)

Rethinking Speech Representation Aggregation in Speech Enhancement: A Phonetic Mutual Information Perspective
by: Han, Seungu, et al.
Published: (2026)

Revealing the Hidden Temporal Structure of HubertSoft Embeddings based on the Russian Phonetic Corpus
by: Ananeva, Anastasia, et al.
Published: (2025)

Dual-View Predictive Diffusion: Lightweight Speech Enhancement via Spectrogram-Image Synergy
by: Xue, Ke, et al.
Published: (2026)

Improving Audio Spectrogram Transformers for Sound Event Detection Through Multi-Stage Training
by: Schmid, Florian, et al.
Published: (2024)

Synthetic Data Domain Adaptation for ASR via LLM-based Text and Phonetic Respelling Augmentation
by: Yamashita, Natsuo, et al.
Published: (2026)

DualSpec: Text-to-spatial-audio Generation via Dual-Spectrogram Guided Diffusion Model
by: Zhao, Lei, et al.
Published: (2025)

Enhancing Spectrogram Realism in Singing Voice Synthesis via Explicit Bandwidth Extension Prior to Vocoder
by: Yang, Runxuan, et al.
Published: (2025)

Few-Shot and Pseudo-Label Guided Speech Quality Evaluation with Large Language Models
by: Zezario, Ryandhimas E., et al.
Published: (2026)

SELEBI: Percussion-aware Time Stretching via Selective Magnitude Spectrogram Compression by Nonstationary Gabor Transform
by: Akaishi, Natsuki, et al.
Published: (2026)

DMF2Mel: A Dynamic Multiscale Fusion Network for EEG-Driven Mel Spectrogram Reconstruction
by: Fan, Cunhang, et al.
Published: (2025)

Attention-weighted Centered Kernel Alignment for Knowledge Distillation in Large Audio-Language Models Applied to Speech Emotion Recognition
by: Yang, Qingran, et al.
Published: (2026)

SSM2Mel: State Space Model to Reconstruct Mel Spectrogram from the EEG
by: Fan, Cunhang, et al.
Published: (2025)

A Real-Time Lyrics Alignment System Using Chroma And Phonetic Features For Classical Vocal Performance
by: Park, Jiyun, et al.
Published: (2024)

Speech-Declipping Transformer with Complex Spectrogram and Learnerble Temporal Features
by: Kwon, Younghoo, et al.
Published: (2024)

Zero-Shot Recognition of Dysarthric Speech Using Commercial Automatic Speech Recognition and Multimodal Large Language Models
by: Alsayegh, Ali, et al.
Published: (2025)

Wavehax: Aliasing-Free Neural Waveform Synthesis Based on 2D Convolution and Harmonic Prior for Reliable Complex Spectrogram Estimation
by: Yoneyama, Reo, et al.
Published: (2024)

Benchmarking Time-localized Explanations for Audio Classification Models
by: Bolaños, Cecilia, et al.
Published: (2025)

SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
by: Stefański, Grzegorz, et al.
Published: (2024)