Yossi Adi

WatermarkNN. Watermarking Deep Neural Networks (USENIX 2018)

GCommandsPytorch. ConvNets for Audio Recognition using Google Commands Dataset

DeepAnomaly. Recurrent Neural Networks for Anomaly Detection using Time Series Data

DeepSegmentor. Sequence Segmentation using Joint RNN and Structured Prediction Models (ICASSP 2017)

AutoVowelDuration. Automatic Measurement of Vowel Duration for Consonant Vowel Consonant (CVC) sound files (JASA 2016)

StructED. Risk Minimization Algorithms in Structured Prediction (JMLR 2016)

Chroma. Pitch and chroma implementation in java

DeepVOT. Automatic Measurement of Voice Onset Time (VOT) using Deep Recurrent Neural Networks (Interspeech 2016)

InDepth-Analysis. Sentence Representation Analysis

DeepWDM. Recurrent Neural Networks for Word Duration Measurement

diffq. DiffQ performs differentiable quantization using pseudo quantization noise. It can automatically tune the number of bits used per weight or group of weight, in order to achieve a given trade-off between the model size and accuracy.

colman_ml. ML course @ colman

Tools-to-Design-or-Visualize-Architecture-of-Neural-Network. Tools to Design or Visualize Architecture of Neural Network

denoiser. 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.