Speech Emotion Recognition Using Mel Frequency Log Spectrogram and Deep Convolutional Neural Network

Bhangale, Kishor; Kothandaraman, Mohanaprasad

doi:10.1007/978-981-16-4625-6_24

Cited by 23 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, it provides the pollution free nature of the HEV by selection of pollution free sources for the powering the HEV. In recent years, deep learning algorithms have shown noteworthy contributions in various signal processing applications because of their faster conversions, high accuracy, reliability, and effectiveness [6], [7], [12]. In the future, various deep learning-based systems can be employed for driving and vehicle condition data augmentation to create the synthetic data for the simulation using available limited datasets [8], [9], [13].…”

Section: ░ 4 Simulation Results and Discussionmentioning

confidence: 99%

Grey Wolf Optimization Based Energy Management Strategy for Hybrid Electrical Vehicles

Gadge

Pahariya

2022

IJEER

View full text Add to dashboard Cite

Electric vehicles (EVs) are seen as a necessary component of transportation's future growth. However, the performance of batteries related to power density and energy density restricts the adoption of electric vehicles. To make the transition from a conventional car to a pure electric vehicle (PEV), a Hybrid Electric Vehicle's (HEV) Energy Management System (EMS) is crucial. The HEVs are often powered with hybrid electrical sources, therefore it is important to select the optimal power source to improve the HEV performance, minimize the fuel cost and minimize hydrocarbon and nitrogen oxides emission. This paper presents the Grey Wolf Optimization (GWO) algorithm for the control of the power sources in the HEVs based on power requirement and economy. The proposed GWO-based EMS provides optimized switching of the power sources and economical and pollution free control of HEV.

show abstract

Section: ░ 4 Simulation Results and Discussionmentioning

confidence: 99%

Grey Wolf Optimization Based Energy Management Strategy for Hybrid Electrical Vehicles

Gadge

Pahariya

2022

IJEER

View full text Add to dashboard Cite

show abstract

“…The convolution provides the global and local features of the liver CT image that characterizes the unique representation of the normal and cancerous liver area. It gives the spatial and frequencydomain characterization of the CT image [45,46,47]. The convolution feature map 𝐼 for the input liver image Lim and K convolution filters is given by equation 3.…”

Section: Lightweight Dcnn For Alcdmentioning

confidence: 99%

Automatic Liver Cancer Detection Using Deep Convolution Neural Network

Napte,

Mahajan,

Urooj

2023

IEEE Access

View full text Add to dashboard Cite

Automatic liver cancer detection (ALCD) is very crucial in automatic biomedical image analysis diagnosis as it is the largest organ in the body and plays a significant role in the metabolic process as well as the elimination of toxins. In the last decade, various machine and deep learning schemes have been investigated for automatic ALCD using computed tomography (CT) images. However, ALCD in CT images is challenging because of the noise, intricate structure of abdominal computed tomography (CT) images, and textural changes throughout the CT images making liver segmentation a vital challenge that may result in both under-segmentation (u-seg) and over-segmentation (o-seg) of the organ. This paper presents liver segmentation based on the proposed Edge Strengthening Parallel UNet (ESP-UNet) for liver segmentation to avoid the u-seg and o-seg of the liver in CT images. Further, it offered ALCD based on lightweight sequential Deep Convolution Neural Networks (DCNN). The consequences of ESP-UNet DCNN-based ALCD are evaluated based on accuracy, recall, precision, and F1-score. The suggested approach provides a noteworthy improvement in ALCD over the traditional state of arts.

show abstract

“…4 is the downsampling with logarithmic scale of spectrogram (log-spectrogram) was employed, using average pooling and pixel reduction with a 1x6 kernel was intended to reduce the number of initial pixels of the spectrogram to 99x43 pixels as the primary input to the CNN model. This preprocessing method was conducted from previous research and has significant result to make spectrogram feature convertible for small form factor [79][80][81][82][83][84][85].…”

Section: 𝑥(𝜏 𝜔) = ∫ 𝑥(𝑡) 𝜔(𝑛 − 𝜏) 𝑒mentioning

confidence: 99%

Development of Speech Command Control Based TinyML System for Post-Stroke Dysarthria Therapy Device

Riyanta,

Irianta,

Kamiel

2023

Journal of Robotics and Control

View full text Add to dashboard Cite

Post-stroke dysarthria (PSD) is a widespread outcome of a stroke. To help in the objective evaluation of dysarthria, the development of pathological voice recognition and technology has a lot of attention. Soft robotics therapy devices have been received as an alternative rehabilitation and hand grasp assistance for improving activity daily living (ADL). Despite the significant progress in this field, most soft robotic therapy devices use a complex, bulky, lack of pathological voice recognition model, large computational power, and stationary controller. This study aims to develop a portable wirelessly multi-controller with a simulated dysarthric vowel speech in Bahasa Indonesia and non-dysarthric micro speech recognition, using tiny machine learning (TinyMl) system for hardware efficiency. The speech interface using INMP441, compute with a lightweight Deep Convolutional Neural network (DCNN) design and embedded into ESP-32. Feature model using Short Time Fourier Transform (STFT) and fed into CNN. This method has proven useful in micro-speech recognition with low computational power in both speech scenarios with a level of accuracy above 90%. Realtime inference performance on ESP-32 using hand prosthetics, with 3-level household noise intensity respectively 24db,42db, and 62db, and has respectively resulted from 95%, 85%, and 50% Accuracy. Wireless connectivity success rate with both controllers is around 0.2 - 0.5 ms.

show abstract

Speech Emotion Recognition Using Mel Frequency Log Spectrogram and Deep Convolutional Neural Network

Cited by 23 publications

References 18 publications

Grey Wolf Optimization Based Energy Management Strategy for Hybrid Electrical Vehicles

Grey Wolf Optimization Based Energy Management Strategy for Hybrid Electrical Vehicles

Automatic Liver Cancer Detection Using Deep Convolution Neural Network

Development of Speech Command Control Based TinyML System for Post-Stroke Dysarthria Therapy Device

Contact Info

Product

Resources

About