Implementation of Neural Voice Cloning with Few Samples Research Paper by Baidu
speech speech-synthesis encodings speech-processing speaker-embeddings mel-spectrogram voice-cloning speaker-encodings
-
Updated
Feb 23, 2021 - Python
#
mel-spectrogram
Here are 91 public repositories matching this topic...
Language: All
Filter by language
Sort: Most stars
Sort options
Recurrent Neural Network for generating piano MIDI-files from audio (MP3, WAV, etc.)
keras convolutional-neural-network cnn-keras keras-tensorflow recurrent-neural-network tensorflow-magenta cqt-spectrogram constant-q-transform piano-transcription mel-spectrogram audio-to-midi constant-q rnn-keras
-
Updated
Oct 19, 2021 - Jupyter Notebook
End-2-end speech synthesis with recurrent neural networks
text-to-speech neural-network speech character lstm synthesis autoregressive neural phoneme long-short-term-memory mel-spectrogram end-2-end
-
Updated
Feb 24, 2024 - Python
This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.
parallel cnn pytorch transformer spectrogram data-augmentation awgn speech-emotion-recognition stacked attention-lstm mel-spectrogram ravdess-dataset
-
Updated
Nov 10, 2022 - Jupyter Notebook
Easier audio-based machine learning with TensorFlow.
-
Updated
Jun 6, 2025 - Python
CNN 1D vs 2D audio classification
-
Updated
Mar 22, 2019 - Jupyter Notebook
A simple audio feature extraction library
-
Updated
Jul 3, 2019 - Python
A librosa STFT/Fbank/mfcc feature extration written up in PyTorch using 1D Convolutions.
-
Updated
Aug 19, 2022 - Python
Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.
-
Updated
Mar 19, 2021 - Python
Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)
machine-learning sound-processing classification urban-sound-classification audio-processing sound-synthesis sound-classification mel-spectrogram audio-tagging sound-classification-spectrograms urban-sound-8k
-
Updated
Mar 24, 2023 - Jupyter Notebook
Zafar's Audio Functions in Python for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.
python stft mfcc audio-signal-processing discrete-cosine-transform dct dst chromagram mdct cqt-kernel cqt-spectrogram discrete-sine-transform constant-q-transform mel-spectrogram short-time-fourier-transform mel-frequency-cepstral-coefficients mel-filterbank inverse-stft inverse-mdct modified-discrete-cosine-transform
-
Updated
Aug 8, 2025 - Jupyter Notebook
Zafar's Audio Functions in Matlab for audio signal analysis: STFT, inverse STFT, mel filterbank, mel spectrogram, MFCC, CQT kernel, CQT spectrogram, CQT chromagram, DCT, DST, MDCT, inverse MDCT.
matlab stft mfcc audio-signal-processing discrete-cosine-transform dct dst istft chromagram mdct imdct cqt-kernel cqt-spectrogram discrete-sine-transform constant-q-transform mel-spectrogram short-time-fourier-transform mel-frequency-cepstral-coefficients mel-filterbank modified-discrete-cosine-transform
-
Updated
Feb 16, 2024 - Jupyter Notebook
Attention-based Hybrid CNN-LSTM and Spectral Data Augmentation for COVID-19 Diagnosis from Cough Sound
deep-learning convolutional-neural-networks attention-mechanism data-augmentation audio-processing long-short-term-memory mel-spectrogram covid-19 covid-19-dataset spec-augmentation covid-19-disease-diagnosis
-
Updated
Aug 31, 2022 - Python
This study converts piano recordings to mel spectrogram and classifies them by SOTA pre-trained neural network backbones in CV. Comparative experiments show that SqueezeNet achieves a best classification accuracy of 92.37%.|该项目将钢琴录音转为为mel频谱图,使用微调后的前沿计算机视觉领域预训练深度学习骨干网络对其进行分类,对比实验可知SqueezeNet作为最优网络正确率可达92.37%
-
Updated
Sep 19, 2025 - Python
基于梅尔频谱的信号分类和识别
-
Updated
Mar 31, 2023 - Python
Basic wavenet and fftnet vocoder model.
-
Updated
Feb 7, 2022 - Python
Code for "Deep Learning Based EDM Subgenre Classification using Mel-Spectrogram and Tempogram Features" arXiv:2110.08862, 2021.
python deep-learning pytorch music-information-retrieval edm mel-spectrogram genres-classification cnn-pytorch tempogram beatport
-
Updated
Oct 29, 2021 - Python
Framework for one-shot multispeaker system based on Deep Learning
text-to-speech speech tts speech-synthesis tacotron mel-spectrogram wavernn voice-cloning speaker-encoders os-ms-tts
-
Updated
May 30, 2021 - Python
Open Source Implementation of Neural Voice Cloning with Few Audio Samples (Baidu Research)
deep-learning pytorch artificial-intelligence speech-synthesis voice-recognition speaker-recognition speech-processing audio-processing voice-synthesis mel-spectrogram speaker-adaptation speaker-encodings aryan05
-
Updated
Oct 12, 2020 - Python
Cough detection with Log Mel Spectrogram, Wavelet Transform, Deep learning and Transfer learning techniques
machine-learning deep-neural-networks transfer-learning wavelet-transform vgg16-model mel-spectrogram cough-detection
-
Updated
Dec 12, 2020 - Python
Improve this page
Add a description, image, and links to the mel-spectrogram topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the mel-spectrogram topic, visit your repo's landing page and select "manage topics."