Saved in:
Bibliographic Details
Main Authors: Liu, HongYu, Wan, Ruijie, Han, Yueju, Li, Junxin, Lu, Liuxing, He, Chao, Cai, Lihua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.11006
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917080073240576
author Liu, HongYu
Wan, Ruijie
Han, Yueju
Li, Junxin
Lu, Liuxing
He, Chao
Cai, Lihua
author_facet Liu, HongYu
Wan, Ruijie
Han, Yueju
Li, Junxin
Lu, Liuxing
He, Chao
Cai, Lihua
contents Audio classification plays an essential role in sentiment analysis and emotion recognition, especially for analyzing customer attitudes in marketing phone calls. Efficiently categorizing customer purchasing propensity from large volumes of audio data remains challenging. In this work, we propose a novel Multi-Segment Multi-Task Fusion Network (MSMT-FN) that is uniquely designed for addressing this business demand. Evaluations conducted on our proprietary MarketCalls dataset, as well as established benchmarks (CMU-MOSI, CMU-MOSEI, and MELD), show MSMT-FN consistently outperforms or matches state-of-the-art methods. Additionally, our newly curated MarketCalls dataset will be available upon request, and the code base is made accessible at GitHub Repository MSMT-FN, to facilitate further research and advancements in audio classification domain.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11006
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MSMT-FN: Multi-segment Multi-task Fusion Network for Marketing Audio Classification
Liu, HongYu
Wan, Ruijie
Han, Yueju
Li, Junxin
Lu, Liuxing
He, Chao
Cai, Lihua
Sound
Artificial Intelligence
Audio classification plays an essential role in sentiment analysis and emotion recognition, especially for analyzing customer attitudes in marketing phone calls. Efficiently categorizing customer purchasing propensity from large volumes of audio data remains challenging. In this work, we propose a novel Multi-Segment Multi-Task Fusion Network (MSMT-FN) that is uniquely designed for addressing this business demand. Evaluations conducted on our proprietary MarketCalls dataset, as well as established benchmarks (CMU-MOSI, CMU-MOSEI, and MELD), show MSMT-FN consistently outperforms or matches state-of-the-art methods. Additionally, our newly curated MarketCalls dataset will be available upon request, and the code base is made accessible at GitHub Repository MSMT-FN, to facilitate further research and advancements in audio classification domain.
title MSMT-FN: Multi-segment Multi-task Fusion Network for Marketing Audio Classification
topic Sound
Artificial Intelligence
url https://arxiv.org/abs/2511.11006