Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi

Ahmet Kemal Yetkin; Hatice Köse

doi:10.1109/SIU59756.2023.10223785

Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi

Ahmet Kemal Yetkin
, Hatice Köse

Yapay Zeka ve Veri Mühendisliği Bölümü

Istanbul Technical University

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

1 Atıf (Scopus)

Özet

This study proposes a method for recognizing emotions from speech using Mel spectrograms and MFCC features which capture the spectral features of speech signals. To predict emotions from the extracted features from the dataset, Convolutional Neural Networks (CNNs) and finetune pre-trained models are used. Pre-trained models are fine-tuned with some optimizations and one-dimensional convolutional neural network is constructed. The results demonstrate that the proposed method achieved an accuracy rate of over 80% in predicting emotions from speech and show the effectiveness of the approach in a comparative manner.

Tercüme edilen katkı başlığı	Speech-Based Emotion Analysis Using Log-Mel Spectrograms and MFCC Features
Orijinal dil	Türkçe
Ana bilgisayar yayını başlığı	31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023
Yayınlayan	Institute of Electrical and Electronics Engineers Inc.
ISBN (Elektronik)	9798350343557
DOI'lar	https://doi.org/10.1109/SIU59756.2023.10223785
Yayın durumu	Yayınlandı - 2023
Etkinlik	31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023 - Istanbul, Türkiye Süre: 5 Tem 2023 → 8 Tem 2023

Yayın serisi

Adı	31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023
Ülke/Bölge	Türkiye
Şehir	Istanbul
Periyot	5/07/23 → 8/07/23

Bibliyografik not

Publisher Copyright:
© 2023 IEEE.

Keywords

MFCC
log-Mel spectrogram
machine learning
neural networks
speech emotion recognition

Belgeye Erişim

10.1109/SIU59756.2023.10223785

Diğer Dosyalar ve Linkler

Link to publication in Scopus

Alıntı Yap

Yetkin, A. K., & Köse, H. (2023). Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi. In 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023 (31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU59756.2023.10223785

@inproceedings{3e4bfed52fc94f1f8ea88d9fdffc8135,

title = "Log-Mel Spektrogramlari ve MFCC {\"O}zellikleri Kullanilarak Konu{\c s}ma Tabanli Duygu Analizi",

abstract = "This study proposes a method for recognizing emotions from speech using Mel spectrograms and MFCC features which capture the spectral features of speech signals. To predict emotions from the extracted features from the dataset, Convolutional Neural Networks (CNNs) and finetune pre-trained models are used. Pre-trained models are fine-tuned with some optimizations and one-dimensional convolutional neural network is constructed. The results demonstrate that the proposed method achieved an accuracy rate of over 80\% in predicting emotions from speech and show the effectiveness of the approach in a comparative manner.",

keywords = "MFCC, log-Mel spectrogram, machine learning, neural networks, speech emotion recognition",

author = "Yetkin, \{Ahmet Kemal\} and Hatice K{\"o}se",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023 ; Conference date: 05-07-2023 Through 08-07-2023",

year = "2023",

doi = "10.1109/SIU59756.2023.10223785",

language = "T{\"u}rk{\c c}e",

series = "31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023",

address = "United States",

}

Yetkin, AK & Köse, H 2023, Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi. in 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023. 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023, Institute of Electrical and Electronics Engineers Inc., 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023, Istanbul, Türkiye, 5/07/23. https://doi.org/10.1109/SIU59756.2023.10223785

Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi. / Yetkin, Ahmet Kemal; Köse, Hatice.
31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023. Institute of Electrical and Electronics Engineers Inc., 2023. (31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023).

Araştırma sonucu: Kitap/Rapor/Konferans Bildirisinde Bölüm › Konferans katkısı › bilirkişi

TY - GEN

T1 - Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi

AU - Yetkin, Ahmet Kemal

AU - Köse, Hatice

PY - 2023

Y1 - 2023

N2 - This study proposes a method for recognizing emotions from speech using Mel spectrograms and MFCC features which capture the spectral features of speech signals. To predict emotions from the extracted features from the dataset, Convolutional Neural Networks (CNNs) and finetune pre-trained models are used. Pre-trained models are fine-tuned with some optimizations and one-dimensional convolutional neural network is constructed. The results demonstrate that the proposed method achieved an accuracy rate of over 80% in predicting emotions from speech and show the effectiveness of the approach in a comparative manner.

AB - This study proposes a method for recognizing emotions from speech using Mel spectrograms and MFCC features which capture the spectral features of speech signals. To predict emotions from the extracted features from the dataset, Convolutional Neural Networks (CNNs) and finetune pre-trained models are used. Pre-trained models are fine-tuned with some optimizations and one-dimensional convolutional neural network is constructed. The results demonstrate that the proposed method achieved an accuracy rate of over 80% in predicting emotions from speech and show the effectiveness of the approach in a comparative manner.

KW - MFCC

KW - log-Mel spectrogram

KW - machine learning

KW - neural networks

KW - speech emotion recognition

UR - https://www.scopus.com/pages/publications/85173485627

U2 - 10.1109/SIU59756.2023.10223785

DO - 10.1109/SIU59756.2023.10223785

M3 - Konferans katkısı

AN - SCOPUS:85173485627

T3 - 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023

BT - 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023

Y2 - 5 July 2023 through 8 July 2023

ER -

Yetkin AK, Köse H. Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi. In 31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023. Institute of Electrical and Electronics Engineers Inc. 2023. (31st IEEE Conference on Signal Processing and Communications Applications, SIU 2023). doi: 10.1109/SIU59756.2023.10223785

Log-Mel Spektrogramlari ve MFCC Özellikleri Kullanilarak Konuşma Tabanli Duygu Analizi

Özet

Yayın serisi

???event.eventtypes.event.conference???

Bibliyografik not

Keywords

Belgeye Erişim

Diğer Dosyalar ve Linkler

Parmak izi

Alıntı Yap