aascode

1D-Speech-Emotion-Recognition

Speech Emotion Recognition from raw speech signals using 1D CNN-LSTM

An-End-to-End-Multitask-Model-to-Improve-Speech-Emotion-Recognition

code for the ICASSP conference paper

bird_audio_detection_challenge

DenseNets for the detection of singing birds in audio files

EmotiW2018_Group-level_Emotion_Recognition

Code for Group-Level Emotion Recognition Using Hybrid Deep Models Based on Faces, Scenes, Skeletons and Visual Attentions

GM-TCNet

Accepted by Journal of Speech Communication (CCF-B).

Human-Activity-Recognition

Multimodal human activity recognition using wrist-worn wearable sensors.

LOUPE_Keras

Rewrite the LOUPE library (https://github.com/antoine77340/LOUPE) into Keras version. Many learnable pooling or differentiable aggregation methods are covered. (NetVLAD, NetRVLAD, SoftDBoW, NetFV, CG)

Speech-Depression-Detection

Speech-Emotion-Recognition-2

Speech emotion recognition using LSTM, SVM and MLP | 语音情感识别

tf-openpose

Openpose from CMU implemented using Tensorflow with Custom Architecture for fast inference.

aascode/Amazing-Feature-Engineering

Feature engineering is the process of using domain knowledge to extract features from raw data via data mining techniques. These features can be used to improve the performance of machine learning algorithms. Feature engineering can be considered as applied machine learning itself.

aascode/Academic-project-page-template

A project page template for academic papers. Demo at https://eliahuhorwitz.github.io/Academic-project-page-template/

aascode/ACL-2024-WASSA-TASK-2

Code for the paper : Cross-lingual emotion detection through Large Language Models

aascode/Alert_Text_Detector

Alert Text Detector is an NLP-based model that detects alert messages from social media posts. It is built using BERTweet Base and trained on a dataset of 23,000 tweets (alert & non-alert). The model flags emergency-related messages and classifies tweets based on textual content.

aascode/ambient-intelligence

Application for Disruptive Situations Detection in public transports through Speech Emotion Recognition.

aascode/audio-embedding-bias

Notebooks to investigate data set bias in audio embeddings

aascode/BERTweet-XAI

In this project, we fine-tune a BerTweet model for binary classification to predict whether a tweet is hate speech or not. We use an activation function for prediction and SHAP (SHapley Additive exPlanations) to provide insights into the model’s decision-making, highlighting the features that influence the classification.

aascode/Hands-On-Large-Language-Models

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

aascode/hate_speech_detection

Comparison of BERT-Base, BERTweet, RoBERTa, DistilBERT for hate speech detection

aascode/layerwise-analysis

Layer-wise analysis of self-supervised pre-trained speech representations

aascode/LLM_SDoH

aascode/LLMs_SDOH_Integration

Supplemental code: Large Language Models for Integrating Social Determinant of Health Data: A Case Study on Heart Failure 30-Day Readmission Prediction

aascode/MentalLLaMA

This repository introduces MentaLLaMA, the first open-source instruction following large language model for interpretable mental health analysis.

aascode/Nell-SDOH-NLP

aascode/Network-Traffic-Prediction

Ensemble Model for Network Intrusion Detection and Prevention

aascode/paper2speech

Convert any english paper or scientific book to audio

aascode/PDF-Extract-Kit

A Comprehensive Toolkit for High-Quality PDF Content Extraction

aascode/RAG_Techniques

This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. RAG systems combine information retrieval with generative models to provide accurate and contextually rich responses.

aascode/SDOH

Evaluate the impact of social determinants on health outcomes

aascode/SDOH-NLI

Description of the dataset: SDOH-NLI is a natural language inference dataset containing ~30k premise-hypothesis pairs with binary entailment labels in the domain of social and behavioral determinants of health.

aascode/sdoh2

aascode/SDoH3

Large Language Models to Identify Social Determinants of Health in Electronic Health Records | Paper: https://www.nature.com/articles/s41746-023-00970-0

aascode/sdoh_n2c2track2_ucsf_umcu

Code and data annotations for the N2C2 SDOH challenge and follow up article in the Journal of Clinical Epidemiology about downstream impact of NLP in association study results.

aascode/SDoHLLM

Generation of synthetic SDoH data to improve training and validation of SDoH detection in EHR datasets

aascode/SMM4H-24-shared-task-5---LT4SG

aascode/smm4h2024-riga

aascode/Speech_Emotion_Diarization

aascode/Various-Text-Classification

aascode/xai-notebooks

This repo contains a notebook designed to teach different eXplainable AI (XAI) techniques on multiple use cases. It is oriented towards an audience with a basic technical level on ML models.

aascode/XAI-Techniques-in-Machine-Learning-A-Jupyter-Notebook-Series

Explore XAI in ML with Jupyter Notebooks: This repo offers practical demonstrations of various Explainable AI techniques like Counterfactuals, SHAP, and more, suited for diverse applications in fields such as healthcare and finance. Ideal for learners and professionals alike.