کنفرانس مهندسی برق ایران

صفحه اصلی / سی و یکمین کنفرانس بین المللی مهندسی برق

Vision Transformer and Parallel Convolutional Neural Network for Speech Emotion Recognition

نویسندگان :

Saber Hashemi¹ Mohammad Asgari²

1- دانشگاه صداوسیما 2- دانشگاه صدا و سیما

کلمات کلیدی :

speech emotion recognition،vision transformer،convolutional neural network،attention mechanism

چکیده :

Vision transformer (ViT) is a new approach for image processing tasks. The vision transformer splits the image into patches and converts it into a sequence of vectors. This sequence is suitable for the transformer structure. This paper uses the ViT method for speech emotion recognition. Unlike ViT, which splits the image into square patches, we use time frames as patches. Alongside using the frame-based ViT to benefit from its ability to learn global features, we are using a convolutional neural network. The convolutional neural network extracts local features and focuses on the two-dimensional structure of the input. Mel-Frequency Cepstral Coefficients extracted from audio files are used as input for the proposed neural network. Using this model in the RAVDESS dataset, we achieved an unweighted accuracy of 79.2%.

لیست مقالات

لیست مقالات بایگانی شده

Improving Wind Turbines Blades Damage detection by using YOLO BoF and BoS

Reza Mohammadi - Saeed Sharifian

تعیین آرایش بهینه خطوط جهت کاهش فرسایش یقه پایه های بتنی ناشی از تنشهای باد

میثم پوراحمدی نخلی - حمیدرضا فیروزآبادی

جداسازی عروق در تصاویر شبکیه چشم با استفاده از یک روش آستانه گذاری وفقی مبتنی بر اطلاعات محلی و سرتاسری

زهرا نورانی آتشگاه - محمد آراسته - آیدا فولادی وندا

Design, Prototyping and Performance Analysis of a Barometric-Based Soft Force Sensor

Mohammad Reza SheykhAzimi - Mohammad Reza Nayeri - Mehdi Tale Masouleh - Ahmad Kalhor

Sensitive RSNs to Schizophrenia; A graph parameter approach

Shirin Karimian - Farzaneh Keyvanfard - Abbas Nasiraei Moghaddam

Design and Implementation of a Data-Driven Controller for a Two-Wheeled Self-Balancing Robot

Mohammad Akhavan - Haniye Parvahan - Mojtaba Nouri Manzar

Identifying Influential Nodes in Complex Networks by Multiple Attributes Model

Shima Esfandiari - Mostafa Fakhrahmad

The Theory of A Novel Circuit Design For An Identification Processor Using 0.35µm CMOS Technology

Rouhollah Mohammadinasr - Kheirollah Hadidi - Farhad Piri

Design and Application of a Five-Level Cross-Switched Inverter in Low-Voltage Distribution System Voltage Compensation

Mohammad Farhadi-kangarlu - Yousef Neyshabouri - Asra Sotudeh

On the Correction of the Boundary Deformation Errors in Microwave Imaging With Spatial Priors

Seyyed Mohammad Hosseini - Amir Ahmad Shishegar

بیشتر

ثمین همایش، سامانه مدیریت کنفرانس ها و جشنواره ها - نگارش 42.0.4