8 results found Sort:

BShakhovsky
PolyphonicPianoTranscription BShakhovsky
41
238
unknown
9
Recurrent Neural Network for generating piano MIDI-files from audio (MP3, WAV, etc.)
keras cnn-keras rnn-keras constant-q audio-to-midi cqt-spectrogram mel-spectrogram keras-tensorflow tensorflow-magenta piano-transcription constant-q-transform recurrent-neural-network convolutional-neural-network
Created 2018-07-10
15 commits to master branch, last one 3 years ago
tiberiu44
TTS-Cube tiberiu44
45
225
apache-2.0
20
End-2-end speech synthesis with recurrent neural networks
lstm neural speech phoneme character end-2-end synthesis autoregressive neural-network text-to-speech mel-spectrogram long-short-term-memory
Created 2018-07-21
243 commits to master branch, last one 10 months ago
Data-Science-kosta
Speech-Emotion-Classification-with-PyTorch Data-Science-kosta
35
194
unknown
7
This repository contains PyTorch implementation of 4 different models for classification of emotions of the speech.
cnn awgn pytorch stacked parallel spectrogram transformer attention-lstm mel-spectrogram ravdess-dataset data-augmentation speech-emotion-recognition
Created 2020-09-30
28 commits to master branch, last one 2 years ago
spotify
realbook spotify
6
114
apache-2.0
8
Easier audio-based machine learning with TensorFlow.
cqt stft audio librosa tensorflow spectrograms mel-spectrogram machine-learning
Created 2022-12-14
24 commits to main branch, last one 4 months ago
echocatzh
torch-mfcc echocatzh
11
73
mit
2
A librosa STFT/Fbank/mfcc feature extration written up in PyTorch using 1D Convolutions.
filter-bank mel-spectrogram signal-processing short-time-fourier-transform
Created 2020-08-18
15 commits to master branch, last one 2 years ago
zzw922cn
LPC_for_TTS zzw922cn
10
68
unknown
6
Linear Prediction Coefficients estimation from mel-spectrogram implemented in Python based on Levinson-Durbin algorithm.
lpc tts lpcnet vocoder wavernn mel-spectrogram audiocompression
Created 2021-03-19
4 commits to main branch, last one 3 years ago
rednafi
urban-sound-classification rednafi
15
58
mit
4
Urban sound source tagging from an aggregation of four second noisy audio clips via 1D and 2D CNN (Xception)
audio-tagging classification urban-sound-8k mel-spectrogram sound-synthesis audio-processing machine-learning sound-processing sound-classification urban-sound-classification sound-classification-spectrograms
Created 2019-05-03
84 commits to master branch, last one 4 years ago
zafarrafii
Zaf-Python zafarrafii
11
53
unknown
1
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.
dct dst mdct mfcc stft python chromagram cqt-kernel inverse-mdct inverse-stft mel-filterbank cqt-spectrogram mel-spectrogram constant-q-transform audio-signal-processing discrete-sine-transform discrete-cosine-transform short-time-fourier-transform modified-discrete-cosine-transform mel-frequency-cepstral-coefficients
Created 2020-08-17
250 commits to master branch, last one 10 months ago