Results 11 to 20 of about 8,338,200 (223)
A Mel Spectrogram Enhancement Paradigm Based on CWT in Speech Synthesis [PDF]
2024 International Conference on Asian Language Processing (IALP)Acoustic features play an important role in improving the quality of the synthesised speech. Currently, the Mel spectrogram is a widely employed acoustic feature in most acoustic models.
Huaning Tan
exaly +8 more sources
Mel spectrogram-based audio forgery detection using CNN
Signal, Image and Video Processing, 2022 In this time of technology, digital speech can be created and falsified by a very diverse of hardware and software technologies. Audio copy-move forgery is an audio forgery technique that goals to create forged audio by hiding undesirable words or ...
Arda Ustubioglu +2 more
semanticscholar +5 more sources
Applied Sciences (Switzerland), 2023 Predicting the remaining time before the next earthquake based on seismic signals generated in a laboratory setting is a challenging research task that is of significant importance for earthquake hazard assessment.
Tao Xu, Wen Chen, Zhang Bo
exaly +4 more sources
Applied Sciences, 2022 The performance of speaker recognition systems is very well on the datasets without noise and mismatch. However, the performance gets degraded with the environmental noises, channel variation, physical and behavioral changes in speaker.
Wondimu Lambamo +2 more
doaj +2 more sources
Natural TTS Synthesis by Conditioning Wavenet on MEL Spectrogram Predictions [PDF]
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017 This paper describes Tacotron 2, a neural network architecture for speech synthesis directly from text. The system is composed of a recurrent sequence-to-sequence feature prediction network that maps character embeddings to mel-scale spectrograms ...
Jonathan Shen +12 more
semanticscholar +5 more sources
A sinusoidal signal reconstruction method for the inversion of the mel-spectrogram [PDF]
2021 IEEE International Symposium on Multimedia (ISM), 2021 The synthesis of sound via deep learning methods has recently received much attention. Some problems for deep learning approaches to sound synthesis relate to the amount of data needed to specify an audio signal and the necessity of preserving both the long and short time coherence of the synthesised signal.
Natsiou, Anastasia, O'Leary, Sean
openaire +7 more sources
Mel-Spectrogram Inversion via Alternating Direction Method of Multipliers
ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)Accepted to ICASSP ...
Yoshiki Masuyama +2 more
core +9 more sources
Is GAN Necessary for Mel-Spectrogram-Based Neural Vocoder? [PDF]
IEEE Signal Processing LettersRecently, mainstream mel-spectrogram-based neural vocoders rely on generative adversarial network (GAN) for high-fidelity speech generation, e.g., HiFi-GAN and BigVGAN. However, the use of GAN restricts training efficiency and model complexity. Therefore,
Hui-Peng Du +4 more
semanticscholar +4 more sources
Text-only domain adaptation for end-to-end ASR using integrated text-to-mel-spectrogram generator [PDF]
Interspeech, 2023 We propose an end-to-end Automatic Speech Recognition (ASR) system that can be trained on transcribed speech data, text-only data, or a mixture of both. The proposed model uses an integrated auxiliary block for text-based training.
Vladimir Bataev +4 more
semanticscholar +3 more sources
Analisis Akurasi dan Waktu Proses Deteksi Sentimen Menggunakan Image Mel-Spectrogram [PDF]
Techno.ComDalam upaya meningkatkan interaksi manusia-mesin, penelitian deteksi sentimen sudah banyak dilakukan peneliti untuk tujuan tersebut. Seiring dengan berkembangnya Mesin Pembelajaran, penelitian ini akan membandingkan kemampuan empat model klasifikasi ...
Jutono Gondohanindijo
doaj +2 more sources