jcvasquezc / AEspeech
Feature extraction from speech signals based on representation learning strategies using pre-trained autoencoders
☆15Updated last year
Alternatives and similar repositories for AEspeech:
Users that are interested in AEspeech are comparing it to the libraries listed below
- Code for our paper "Acoustic Features Fusion using Attentive Multi-channel Deep Architecture" in Keras and tensorflow☆26Updated 6 years ago
- Inspired by the convolutional recurrent neural network(CRNN) and inception, we propose a multiscale time-frequency convolutional recurren…☆22Updated 4 years ago
- PyTorch implementation of the 1D-Triplet-CNN neural network model described in Fusing MFCC and LPC Features using 1D Triplet CNN for Spea…☆27Updated 5 years ago
- Differentiable short-time Fourier transform (DSTFT): Gradient-based parameters tuning for adaptive time-frequency representation. DSTFT i…☆32Updated 8 months ago
- measures to assess frequency-weighted instantaneous energy☆17Updated 2 years ago
- Official implementation of the Seq-U-Net for efficient sequence modelling☆78Updated 5 months ago
- Evaluation of the classification performance (Speech, Music, and Noise) of 1D (WaveNet) and 2D (MobileNet) CNN and RNN (GRU) on the MUSAN…☆15Updated 4 years ago
- Implementation of deep recurrent nonnegative matrix factorization (DR-NMF) for speech separation☆48Updated 5 years ago
- Joint Estimation of Frequency, Amplitude and Spectrum☆30Updated last year
- Joint Dictionary Learning-based Non-Negative Matrix Factorization for Voice Conversion (TBME 2016)☆22Updated 7 years ago
- Code for Multi Speaker Source Separation with neural networks, build with TensorFlow☆18Updated 4 years ago
- PyTorch Implementation of SubSpectralNet - Using Sub-Spectrogram based Convolutional Neural Networks for Acoustic Scene Classification, a…☆21Updated 5 years ago
- Applying discrete wavelet packet transform (DWPT) and nonnegative matrix factorization (NMF) analysis to speech enhancement tasks. Conven…☆11Updated 7 years ago
- ICML 21 - Voice2Series: Adversarial Reprogramming Acoustic Models for Time Series Classification☆70Updated 7 months ago
- Learning discriminative and robust time-frequency representations for environmental sound classification: Convolutional neural networks (…☆28Updated 5 years ago
- ☆16Updated 5 years ago
- Generative Adversarial Network implemented for the Time-Frequency based Speech Enhancement☆8Updated 8 months ago
- Adversarial Unsupervised Domain Adaptation for Acoustic Scene Classification☆35Updated 6 years ago
- A python version of fast and robust ICA based on the paper of Aapo Hyvärinen.☆29Updated last year
- Tensorflow implementation of a CycleGAN with a 1D Convolutional Neural Network and Gated units with options for the residual connections,…☆23Updated 6 years ago
- Kalman filtering for speech signal enhancement☆19Updated 8 years ago
- Audio MNIST Classification using 1D-CNN, 2D-CNN, GAN+2D-CNN, CVN+RandomForest, and LSTMs.☆14Updated 3 years ago
- SELD-TCN: Sound Event Detection & Localization via Temporal Convolutional Network | Python w/ Tensorflow☆62Updated 4 years ago
- Bag-of-Features Acoustic Event Detection☆14Updated 8 years ago
- Directional sparse filtering for blind speech separation☆9Updated 3 years ago
- Pytorch implementation of [Learning to match transient sound events using attentional similarity for few-shot sound recognition]☆33Updated 5 years ago
- Denoising autoencoders for speaker identification on MCE 2018 challenge☆12Updated 6 years ago
- Classification of environmental sounds using 1D convolutional Neural network☆32Updated 4 years ago
- The project is related to the development of labs for the ITMO Speaker Recognition Course.☆10Updated 2 years ago
- Implementation of the multi-time-scale convolution layer used in the paper Multi-Time-Scale Convolution for Emotion Recognition from Spee…☆11Updated 5 years ago