Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Gogoi, Parismita, Singh, Vishwanath Pratap, Khadirnaikar, Seema, Siddhartha, Soma, Kalita, Sishir, Mishra, Jagabandhu, Sahidullah, Md, Sarmah, Priyankoo, Prasanna, S. R. M.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916793750126592
author Gogoi, Parismita
Singh, Vishwanath Pratap
Khadirnaikar, Seema
Siddhartha, Soma
Kalita, Sishir
Mishra, Jagabandhu
Sahidullah, Md
Sarmah, Priyankoo
Prasanna, S. R. M.
author_facet Gogoi, Parismita
Singh, Vishwanath Pratap
Khadirnaikar, Seema
Siddhartha, Soma
Kalita, Sishir
Mishra, Jagabandhu
Sahidullah, Md
Sarmah, Priyankoo
Prasanna, S. R. M.
contents This study explores the potential of Rhythm Formant Analysis (RFA) to capture long-term temporal modulations in dementia speech. Specifically, we introduce RFA-derived rhythm spectrograms as novel features for dementia classification and regression tasks. We propose two methodologies: (1) handcrafted features derived from rhythm spectrograms, and (2) a data-driven fusion approach, integrating proposed RFA-derived rhythm spectrograms with vision transformer (ViT) for acoustic representations along with BERT-based linguistic embeddings. We compare these with existing features. Notably, our handcrafted features outperform eGeMAPs with a relative improvement of $14.2\%$ in classification accuracy and comparable performance in the regression task. The fusion approach also shows improvement, with RFA spectrograms surpassing Mel spectrograms in classification by around a relative improvement of $13.1\%$ and a comparable regression score with the baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00861
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment
Gogoi, Parismita
Singh, Vishwanath Pratap
Khadirnaikar, Seema
Siddhartha, Soma
Kalita, Sishir
Mishra, Jagabandhu
Sahidullah, Md
Sarmah, Priyankoo
Prasanna, S. R. M.
Audio and Speech Processing
Sound
This study explores the potential of Rhythm Formant Analysis (RFA) to capture long-term temporal modulations in dementia speech. Specifically, we introduce RFA-derived rhythm spectrograms as novel features for dementia classification and regression tasks. We propose two methodologies: (1) handcrafted features derived from rhythm spectrograms, and (2) a data-driven fusion approach, integrating proposed RFA-derived rhythm spectrograms with vision transformer (ViT) for acoustic representations along with BERT-based linguistic embeddings. We compare these with existing features. Notably, our handcrafted features outperform eGeMAPs with a relative improvement of $14.2\%$ in classification accuracy and comparable performance in the regression task. The fusion approach also shows improvement, with RFA spectrograms surpassing Mel spectrograms in classification by around a relative improvement of $13.1\%$ and a comparable regression score with the baselines.
title Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2506.00861