Fernando López Gavilánez's Projects
A Convolutional Transformer for Keyword Spotting (AAAI 2022 DSTC Workshop)
UrbanSound classification using Convolutional Recurrent Networks in PyTorch
A PyTorch implementation of CTCLoss (for learning purposes)
Segment an audio file and obtain utterance alignments. (Python package)
Deep Effect Generation using GANs
Real Time Speech Enhancement in the Waveform Domain (Interspeech 2020)We provide a PyTorch implementation of the paper Real Time Speech Enhancement in the Waveform Domain. In which, we present a causal speech enhancement model working on the raw waveform that runs in real-time on a laptop CPU. The proposed model is based on an encoder-decoder architecture with skip-connections. It is optimized on both time and frequency domains, using multiple loss functions. Empirical evidence shows that it is capable of removing various kinds of background noise including stationary and non-stationary noises, as well as room reverb. Additionally, we suggest a set of data augmentation techniques applied directly on the raw waveform which further improve model performance and its generalization abilities.
Domestic environment sound event detection task
Lightweight python library for streaming speaker diarization in real-time implemented in pytorch
TensorFlow examples
W. Fernando López Gavilánez public page
The code for the https://arxiv.org/pdf/2210.15226.pdf
An implementation of Performer, a linear attention-based transformer, in Pytorch
Several pytorch projects
Efficient Keyword Spotting
Torch implementation of Sonopy
Speaker Recognition Exploration
A PyTorch-based Speech Toolkit
Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".
Example code for a neural transducer model.
Transformer-based Spanish corrector
Udacity Deep Learning Course
Baseline of the Wake-up Word Challenge of the 2024 Albayzin Evaluations