Drone Classification with a Hybrid Deep Learning Approach Based on Mel-Spectrogram Representation
With technological advancements, the use of drones has become increasingly widespread in both civilian and military sectors in recent years. There is a need for technologies that can detect and identify the presence, type, or flight mode of a drone with ...
Özbek, İbrahim Yücel +3 more
core +1 more source
Gender Recognition Based on the Stacking of Different Acoustic Features
Applied SciencesA speech signal can provide various information about a speaker, such as their gender, age, accent, and emotional state. The gender of the speaker is the most salient piece of information contained in the speech signal and is directly or indirectly used ...
Ergün Yücesoy
doaj +1 more source
High-quality Speech Synthesis Using Super-resolution Mel-Spectrogram
CoRR, 2019 In speech synthesis and speech enhancement systems, melspectrograms need to be precise in acoustic representations. However, the generated spectrograms are over-smooth, that could not produce high quality synthesized speech. Inspired by image-to-image translation, we address this problem by using a learning-based post filter combining Pix2PixHD and ...
Leyuan Sheng +2 more
openaire +2 more sources
Age Prediction from Korean Speech Data Using Neural Networks with Diverse Voice Features
Applied SciencesA person’s voice serves as an indicator of age, as it changes with anatomical and physiological influences throughout their life. Although age prediction is a subject of interest across various disciplines, age-prediction studies using Korean voices are ...
Hayeon Ku +4 more
doaj +1 more source
TranStutter: A Convolution-Free Transformer-Based Deep Learning Method to Classify Stuttered Speech Using 2D Mel-Spectrogram Visualization and Attention-Based Feature Representation. [PDF]
Sensors (Basel), 2023 Basak K, Mishra N, Chang HT.
europepmc +1 more source
Active Defense Against Voice Conversion Through Generative Adversarial Network [PDF]
Active defense is an important approach to counter speech deepfakes that threaten individuals’ privacy, property, and reputation. However, the existing works in this field suffer from issues such as time-consuming and ordinary defense effectiveness. This
Zhao, Guoying +3 more
core +1 more source
Marine Mammal Call Classification Using a Multi-Scale Two-Channel Fusion Network (MT-Resformer)
Journal of Marine Science and EngineeringThe classification of high-frequency marine mammal vocalizations often faces challenges due to the limitations of acoustic features, which are sensitive to mid-to-low frequencies but offer low resolution in high-frequency ranges.
Xiang Li +6 more
doaj +1 more source
Multi-Label Emotion Recognition of Korean Speech Data Using Deep Fusion Models
Applied SciencesAs speech is the most natural way for humans to express emotions, studies on Speech Emotion Recognition (SER) have been conducted in various ways However, there are some areas for improvement in previous SER studies: (1) while some studies have performed
Seoin Park +3 more
doaj +1 more source
IEEE AccessThis study proposes an innovative speech translation method based on Pix2PixGAN, which maps the Mel spectrograms of speech produced by deaf individuals to those of normal-hearing individuals and generates semantically coherent speech output.
Shaoting Zeng +5 more
doaj +1 more source
ESTVocoder: An Excitation-Spectral-Transformed Neural Vocoder Conditioned on Mel Spectrogram
This paper proposes ESTVocoder, a novel excitation-spectral-transformed neural vocoder within the framework of source-filter theory. The ESTVocoder transforms the amplitude and phase spectra of the excitation into the corresponding speech amplitude and phase spectra using a neural filter whose backbone is ConvNeXt v2 blocks.
Xiao-Hang Jiang +4 more
openaire +2 more sources