Results 41 to 50 of about 7,229,432 (222)
Percussion-Based Pipeline Ponding Detection Using a Convolutional Neural Network
Applied Sciences, 2022 Pipeline transportation is the main method for long-distance gas transportation; however, ponding in the pipeline can affect transportation efficiency and even cause corrosion to the pipeline in some cases.
Dan Yang +3 more
doaj +1 more source
Deep learning bird song recognition based on MFF-ScSEnet
Ecological Indicators, 2023 Bird diversity plays an important role in ecological balance, and bird song identification is of great practical significance. The spectrum generated by feature extraction shows good performance on classification.
Shipeng Hu +5 more
doaj +1 more source
Iterating over 28,500 steps of the Mel-spectrogram.
, 2023 Iterating over 28,500 steps of the Mel-spectrogram.
Xianyou Zhu (11588965) +1 more
core +1 more source
Applied Sciences, 2021 In this paper, feature extraction methods are developed based on the non-negative matrix factorization (NMF) algorithm to be applied in weakly supervised sound event detection. Recently, the development of various features and systems have been attempted
Seokjin Lee +4 more
doaj +1 more source
Applied Sciences, 2019 We evaluated electrocardiogram (ECG) biometrics using pre-configured models of convolutional neural networks (CNNs) with various time-frequency representations.
Yeong-Hyeon Byeon, Keun-Chang Kwak
doaj +1 more source
Mel frequency spectral domain defenses against adversarial attacks on speech recognition systems [PDF]
JASA Express Letters, 2023 Automatic speech recognition (ASR) systems are vulnerable to adversarial attacks due to their reliance on machine learning models. Many of the defenses explored for defending ASR systems simply adapt defense approaches developed for the image domain ...
Nicholas Mehlman +3 more
doaj +1 more source
Mel-spectrogram features for acoustic vehicle detection and speed estimation
2022 26th International Conference on Information Technology (IT), 2022 The paper addresses acoustic vehicle detection and speed estimation from single sensor measurements. We predict the vehicle's pass-by instant by minimizing clipped vehicle-to-microphone distance, which is predicted from the mel-spectrogram of input audio, in a supervised learning approach.
Nikola Bulatovic, Slobodan Djukanovic
openaire +2 more sources
Feature selection for emotion recognition in speech: a comparative study of filter and wrapper methods [PDF]
PeerJ Computer ScienceFeature selection is essential for enhancing the performance and reducing the complexity of speech emotion recognition models. This article evaluates various feature selection methods, including correlation-based (CB), mutual information (MI), and ...
Alaa Altheneyan, Aseel Alhadlaq
doaj +2 more sources
CycleGAN-VC3: Examining and Improving CycleGAN-VCs for Mel-Spectrogram Conversion [PDF]
Interspeech 2020, 2020 Non-parallel voice conversion (VC) is a technique for learning mappings between source and target speeches without using a parallel corpus. Recently, cycle-consistent adversarial network (CycleGAN)-VC and CycleGAN-VC2 have shown promising results regarding this problem and have been widely used as benchmark methods.
Takuhiro Kaneko +3 more
openaire +2 more sources
A Hybrid CNN and RNN Variant Model for Music Classification
Applied Sciences, 2023 Music genre classification has a significant role in information retrieval for the organization of growing collections of music. It is challenging to classify music with reliable accuracy.
Mohsin Ashraf +6 more
doaj +1 more source