PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Phukan, Orchid Chetia, Akhtar, Mohd Mujtaba, Girish, Behera, Swarup Ranjan, Patibandla, Jaya Sai Kiran, Buduru, Arun Balaji, Sharma, Rajesh
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915317850046464
author Phukan, Orchid Chetia
Akhtar, Mohd Mujtaba
Girish
Behera, Swarup Ranjan
Patibandla, Jaya Sai Kiran
Buduru, Arun Balaji
Sharma, Rajesh
author_facet Phukan, Orchid Chetia
Akhtar, Mohd Mujtaba
Girish
Behera, Swarup Ranjan
Patibandla, Jaya Sai Kiran
Buduru, Arun Balaji
Sharma, Rajesh
contents The emergence of Mamba as an alternative to attention-based architectures has led to the development of Mamba-based self-supervised learning (SSL) pre-trained models (PTMs) for speech and audio processing. Recent studies suggest that these models achieve comparable or superior performance to state-of-the-art (SOTA) attention-based PTMs for speech emotion recognition (SER). Motivated by prior work demonstrating the benefits of PTM fusion across different speech processing tasks, we hypothesize that leveraging the complementary strengths of Mamba-based and attention-based PTMs will enhance SER performance beyond the fusion of homogenous attention-based PTMs. To this end, we introduce a novel framework, PARROT that integrates parallel branch fusion with Optimal Transport and Hadamard Product. Our approach achieves SOTA results against individual PTMs, homogeneous PTMs fusion, and baseline fusion techniques, thus, highlighting the potential of heterogeneous PTM fusion for SER.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01138
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition
Phukan, Orchid Chetia
Akhtar, Mohd Mujtaba
Girish
Behera, Swarup Ranjan
Patibandla, Jaya Sai Kiran
Buduru, Arun Balaji
Sharma, Rajesh
Audio and Speech Processing
Sound
The emergence of Mamba as an alternative to attention-based architectures has led to the development of Mamba-based self-supervised learning (SSL) pre-trained models (PTMs) for speech and audio processing. Recent studies suggest that these models achieve comparable or superior performance to state-of-the-art (SOTA) attention-based PTMs for speech emotion recognition (SER). Motivated by prior work demonstrating the benefits of PTM fusion across different speech processing tasks, we hypothesize that leveraging the complementary strengths of Mamba-based and attention-based PTMs will enhance SER performance beyond the fusion of homogenous attention-based PTMs. To this end, we introduce a novel framework, PARROT that integrates parallel branch fusion with Optimal Transport and Hadamard Product. Our approach achieves SOTA results against individual PTMs, homogeneous PTMs fusion, and baseline fusion techniques, thus, highlighting the potential of heterogeneous PTM fusion for SER.
title PARROT: Synergizing Mamba and Attention-based SSL Pre-Trained Models via Parallel Branch Hadamard Optimal Transport for Speech Emotion Recognition
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2506.01138