0% Complete
فارسی
Home
/
شانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش
A Deep Learning Framework for Phase-Aware Feature Representation to Improve Sound Source Direction and Distance Estimation
Authors :
Zahra Abolfazli
1
Hamid Reza Abutalebi
2
1- Yazd University
2- Yazd University
Keywords :
(Sound Event Localization and Detection (SELD،phase spectrogram features،Conformer
Abstract :
This paper proposes a novel refinement of the network’s input features to improve distance and Direction-of-Arrival estimation in the sound event localization and detection system. Instead of relying on Mel energies, we propose using phase spectrograms as input feature, which effectively preserve inter-channel time delays and capture crucial wave propagation characteristics. Furthermore, we introduce architectural improvements for increased robustness. Specifically, Huber loss replaces MSE, reducing sensitivity to noise. Additionally, MHSA layers are replaced with Conformer blocks to better model both long-range dependencies and local interactions within the audio data. Our experimental results validate the effectiveness of the proposed phase-based feature representation and optimized architecture, demonstrating improvements in both DOA and distance estimation.
Papers List
List of archived papers
Paths-oriented Test Data Generation using Genetic Algorithm
Mohammad Reza Hassanpour Charmchi - Dr Bagher Rahimpour cami
A Fuzzy Cluster-Based Routing Algorithm to Extend Wireless Sensor Network Lifetime
Mostafa Mirzaie - Armin Mazinani - Dr Sayyed Majid Mazinani
A High-Speed Quantum Reversible Controlled Adder/Subtractor Circuit
Negin Mashayekhi - Mohammad Reza Reshadinezhad - Shekoofeh Moghimi
یک سیستم پاسخ به نفوذ در شبکه های اینترنت اشیاء با استفاده از شبکه های مبتنی بر نرم افزار
احسان شاهرخی مینا - رضا محمدی - محمد نصیری
AI-Driven Approach to Detect Equivalent Elements within Domain Models
Mohammad-Sajad Kasaei - Mohammadreza Sharbaf - Afsaneh Fatemi - Bahman Zamani
Robustness Gap in NLP Models for Vulnerability Descriptions: Benchmarking and Data Augmentation
AmirHossein Majd - Mahdi Yousefikia - Saghar Ghasemzadeh - Amirreza Asari - Arya Khoshnavataher - Seyedeh Leili Mirtaheri
A Mathematical Optimization Approach for Preference Learning in Movie Recommender Systems with Shared Accounts
Milad Khademali - Fazlollah Aghamohammadi - Marjan Kaedi - Alireza Nasiri
Sigma: A Secure Federated Network Gaming Platform
Keyhan Mohammadi - Reza Ebrahimi Atani
پیش بینی گره های رهبر در شبکه های اجتماعی با استفاده از پیش بینی پیوند
روح اله رشیدی - فرساد زمانی بروجنی - محمد رضا سلطان آقایی - هادی فرهادی
تخلیهبار محاسباتی ریزدانه تحرکآگاه در رایانش لبه برای اینترنت اشیاء
شکوفه نوروزی - دکتر زینب موحدی شکوفه نوروزی - زینب موحدی -
more
Samin Hamayesh - Version 42.5.2