Curated list of open source tooling for data-centric AI on unstructured data.

Multilingual Automatic Speech Recognition with word-level timestamps and confidence

A streaming uploader for ESP32 that supports large files and https

Light-SERNet: A lightweight fully convolutional neural network for speech emotion recognition

Safety health wearable and app tailored to the elderly, people with dangerous health conditions, and people who suffer from memory loss.

Cough detection with Log Mel Spectrogram, Wavelet Transform, Deep learning and Transfer learning techniques

Code reference for the paper

Predicting In-hospital Mortality of Patients in the Pediatric ICU

Author's repository for reproducing DcaseNet, an integrated pre-trained DNN that performs acoustic scene classification, audio tagging, and sound event detection. Implemented using PyTorch.

Multimodal Transformer for Korean Sentiment Analysis with Audio and Text Features

A library to generate LaTeX expression from Python code.

InceptionTime: Finding AlexNet for Time Series Classification

Reproducible Research Framework for Multimodal Affect and Action Recognition at Utterance-Level with Spatio-Temporal Feature Fusion by using Face, Instantaneous Emotions, Audio, Text, and Body Feat…

Multi-modal Speech Emotion Recogniton on IEMOCAP dataset

📐 Compute distance between sequences. 30+ algorithms, pure python implementation, common interface, optional external libs usage.

Head pose estimation by TensorFlow and OpenCV

8th place solution (on Kaggle) to the Freesound General-Purpose Audio Tagging Challenge (DCASE 2018 - Task 2)

Pitch estimation network (PiENet) for noise-robust neural F0 estimation of speech signals

ERNIE Pytorch Version

Conditional RNNs for Tensorflow / Keras.

CNN-based audio segmentation toolkit. Allows to detect speech, music, noise and speaker gender. Has been designed for large scale gender equality studies based on speech time per gender.

OpenMMLab Detection Toolbox and Benchmark

ocr detect using psenet

A collection of various deep learning architectures, models, and tips

Awesome work on hand pose estimation/tracking

A skeleton-based real-time online action recognition project, classifying and recognizing base on framewise joints, which can be used for safety surveilence.