Results 171 to 180 of about 7,229,432 (222)

Restoration of Acoustic Identity via Artificial Intelligence-Driven Neural Voice Conversion for Total Laryngectomy Patients: A Technical Framework for Biometric Security and Social Inclusion. [PDF]

Cureus
Girgin MC, Can C, Onucak Girgin P, Ozer BS.   +3 more
europepmc   +1 more source

CleanMel: Mel-Spectrogram Enhancement for Improving Both Speech Quality and ASR

IEEE Transactions on Audio, Speech and Language Processing
In this work, we propose CleanMel, a single-channel Mel-spectrogram denoising and dereverberation network for improving both speech quality and automatic speech recognition (ASR) performance.
Nian Shao, Pengyu Wang, Xiaofei Li
exaly   +4 more sources

Mel-Refine: A Plug-and-Play Approach to Refine Mel-Spectrogram in Audio Generation

CoRR
Mainstream Text-to-Audio (TTA) models that rely on Mel-spectrograms often struggle to generate audio with rich content, leading to blurred or incoherent outputs. This stems from an inability to model intricate spectral details and textures.
Hongming Guo, Ruibo Fu, Yizhong Geng, Shuai Liu, Shuchen Shi, Tao Wang, Chunyu Qiang, Chenxing Li, Ya Li, Zhengqi Wen, Yukun Liu, Xuefei Liu   +11 more
semanticscholar   +4 more sources

Mel Spectrogram-Based CNN Framework for Explainable Audio Deepfake Detection

International Conference on Advanced Information Networking and Applications
The rise of audio deepfakes is becoming a growing concern for media credibility, particularly on social platforms. This study explores an approach to detecting audio deepfakes using Convolutional Neural Networks (CNNs) applied to Mel spectrograms, which serve as visual representations of audio signals.
Muhammad Khurram Zahur Bajwa, Aniello Castiglione, Chiara Pero   +2 more
semanticscholar   +4 more sources

Some of the next articles are maybe not open access.

Related searches:

Underwater target recognition using convolutional recurrent neural networks with 3-D Mel-spectrogram and data augmentation

Applied Acoustics, 2021
Passive recognition of underwater acoustic targets is a hot research issue in acoustic signal processing. The long-term interference of irregular noise in the marine environment caused the relevance of the passive recognition method of underwater targets
Tongsheng Shen, Dexin Zhao
exaly   +2 more sources

MelRe: Vision-Based Mel-Spectrogram Restoration

Interspeech 2025
With advancements in visual technology, an increasing number of visual techniques have recently been applied in other fields. Among them, mel spectrograms provide a bridge between audio features and visual models.
Kaixuan Luan, Xiaoda Yang, Shile Cai, Ruofan Hu, Minghui Fang, Wenrui Liu, Jialong Zuo, Jiaqi Duan, Yuhang Ma, JunYu Lu   +9 more
semanticscholar   +2 more sources

DMEL: The Differentiable Log-Mel Spectrogram as a Trainable Layer in Neural Networks

IEEE International Conference on Acoustics, Speech, and Signal Processing
In this paper we present the differentiable log-Mel spectrogram (DMEL) for audio classification. DMEL uses a Gaussian window, with a window length that can be jointly optimized with the neural network.
John Martinsson, Maria Sandsten
semanticscholar   +3 more sources