AI grand challenge 2020 Repo (Speech Recognition Track)

Overview

KorBERT를 활용한 한국어 텍스트 기반 위협 상황인지(2020 인공지능 그랜드 챌린지)

본 프로젝트는 ETRI에서 제공된 한국어 korBERT 모델을 활용하여 폭력 기반 한국어 텍스트를 분류하는 다양한 분류 모델들을 제공합니다.

본 개발자들이 참여한 2020 인공지능 그랜드 챌린지 4차 대회는 인공지능 기술을 활용하여 다양한 지역사회의 국민생활 및 사회현안을 대응하는 과제입니다. 그중 음성인지 트랙은 음성 클립에서 위협상황을 검출하고 해당 위협 상황을 구분하는 것이 목표로 하고 있습니다. 아래의 표는 본 대회에서 정의한 4가지의 폭력 Class이며 아래의 4가지 폭력 Class 외에 비폭력 Class가 추가되어 총 5개 Class의 폭력 또는 비폭력을 분류하는 것이 주된 목적입니다.

< 음성인지 분류대상 정의 >

추가적으로, 본 개발자들은 ETRI에서 작성된 사용협약서에 준수하여 pretrained 모델 및 정보에 관한 내용은 공개하지 않습니다. 해당 프로젝트를 쉽게 활용하기 위해서는 ETRI에서 제공하는 API를 활용하시면 되며, 다음 링크에서 서약서를 작성 후 키와 코드를 다운받으시면 되십니다. 본 프로젝트는 대회에서 적용한 여러 분류 모델들을 제공하며 앞서 다운로드한 ETRI에서 제공된 형태소 분석기와 토큰화를 사용하여 쉽게 실습할 수 있습니다.

분류 모델

Requirements

Python 3.7

Pytorch == 1.5.0

boto3

botocore

tqdm

requests

Models

본 프로젝트는 4가지의 분류 모델(MLP, CNN, LSTM, Bi-LSTM)을 활용하였습니다. 아래는 활용된 모델들의 전체적인 시나리오를 보여주는 개요도입니다.

1. MLP

< 활용된 MLP 모델 >

2. CNN

CNN은 해당 논문을 참고하였습니다. 더 자세한 내용은 논문에서 확인할 수 있습니다.

< 활용된 CNN 모델 >

3. LSTM

< 활용된 LSTM 모델 >

4. Bi-LSTM

< 활용된 Bi-LSTM 모델 >

Results

본 대회에서는 분류 결과를 Macro-F1 score에 의해 평가하였으며, Macro-F1 score는 아래와 같이 정의합니다. 이때, i는 각각의 폭력 및 비폭력 Class를 의미합니다.

< Macro-F1 Score >

위 식을 토대로, 저희의 분류 아래의 결과는 2020 인공지능 그랜드 챌린지 4차 대회 음성인지 트랙에서 본 팀에 대한 결과이며, 주최 측에서 테스트 데이터는 공개하지 않아 확인할 수 없습니다.

Model MLP [1] CNN [2] LSTM [3] Bi-LSTM [4]
Macro F1-Score 0.7029 0.615 0.7157 0.6935
Owner
Young-Seok Choi
Young-Seok Choi
Code for the Convolutional Vision Transformer (ConViT)

ConViT : Vision Transformers with Convolutional Inductive Biases This repository contains PyTorch code for ConViT. It builds on code from the Data-Eff

Facebook Research 418 Jan 06, 2023
Alphabetical Letter Recognition

DecisionTrees-Image-Classification Alphabetical Letter Recognition In these demo we are using "Decision Trees" Our database is composed by Learning Im

Mohammed Firass 4 Nov 30, 2021
"Learning Free Gait Transition for Quadruped Robots vis Phase-Guided Controller"

PhaseGuidedControl The current version is developed based on the old version of RaiSim series, and possibly requires further modification. It will be

X-Mechanics 12 Oct 21, 2022
MoCoGAN: Decomposing Motion and Content for Video Generation

MoCoGAN: Decomposing Motion and Content for Video Generation This repository contains an implementation and further details of MoCoGAN: Decomposing Mo

Sergey Tulyakov 514 Dec 18, 2022
Convolutional Neural Network to detect deforestation in the Amazon Rainforest

Convolutional Neural Network to detect deforestation in the Amazon Rainforest This project is part of my final work as an Aerospace Engineering studen

5 Feb 17, 2022
Multi Agent Reinforcement Learning for ROS in 2D Simulation Environments

IROS21 information To test the code and reproduce the experiments, follow the installation steps in Installation.md. Afterwards, follow the steps in E

11 Oct 29, 2022
A stock generator that assess a list of stocks and returns the best stocks for investing and money allocations based on users choices of volatility, duration and number of stocks

Stock-Generator Please visit "Stock Generator.ipynb" for a clearer view and "Stock Generator.py" for scripts. The stock generator is designed to allow

jmengnyay 1 Aug 02, 2022
A fast MoE impl for PyTorch

An easy-to-use and efficient system to support the Mixture of Experts (MoE) model for PyTorch.

Rick Ho 873 Jan 09, 2023
A framework for Quantification written in Python

QuaPy QuaPy is an open source framework for quantification (a.k.a. supervised prevalence estimation, or learning to quantify) written in Python. QuaPy

41 Dec 14, 2022
ReSSL: Relational Self-Supervised Learning with Weak Augmentation

ReSSL: Relational Self-Supervised Learning with Weak Augmentation This repository contains PyTorch evaluation code, training code and pretrained model

mingkai 45 Oct 25, 2022
TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Prediction.

TalkNet 2 [WIP] TalkNet 2: Non-Autoregressive Depth-Wise Separable Convolutional Model for Speech Synthesis with Explicit Pitch and Duration Predictio

Rishikesh (ऋषिकेश) 69 Dec 17, 2022
PyTorch implementation of DeepLab v2 on COCO-Stuff / PASCAL VOC

DeepLab with PyTorch This is an unofficial PyTorch implementation of DeepLab v2 [1] with a ResNet-101 backbone. COCO-Stuff dataset [2] and PASCAL VOC

Kazuto Nakashima 995 Jan 08, 2023
Code of Adverse Weather Image Translation with Asymmetric and Uncertainty aware GAN

Adverse Weather Image Translation with Asymmetric and Uncertainty-aware GAN (AU-GAN) Official Tensorflow implementation of Adverse Weather Image Trans

Jeong-gi Kwak 36 Dec 26, 2022
A fast, dataset-agnostic, deep visual search engine for digital art history

imgs.ai imgs.ai is a fast, dataset-agnostic, deep visual search engine for digital art history based on neural network embeddings. It utilizes modern

Fabian Offert 5 Dec 14, 2022
Implementation of Basic Machine Learning Algorithms on small datasets using Scikit Learn.

Basic Machine Learning Algorithms All the basic Machine Learning Algorithms are implemented in Python using libraries Acknowledgements Machine Learnin

Piyal Banik 47 Oct 16, 2022
Easy-to-use micro-wrappers for Gym and PettingZoo based RL Environments

SuperSuit introduces a collection of small functions which can wrap reinforcement learning environments to do preprocessing ('microwrappers'). We supp

Farama Foundation 357 Jan 06, 2023
A basic implementation of Layer-wise Relevance Propagation (LRP) in PyTorch.

Layer-wise Relevance Propagation (LRP) in PyTorch Basic unsupervised implementation of Layer-wise Relevance Propagation (Bach et al., Montavon et al.)

Kai Fabi 28 Dec 26, 2022
Sound Event Detection with FilterAugment

Sound Event Detection with FilterAugment Official implementation of Heavily Augmented Sound Event Detection utilizing Weak Predictions (DCASE2021 Chal

43 Aug 28, 2022
Segmentation Training Pipeline

Segmentation Training Pipeline This package is a part of Musket ML framework. Reasons to use Segmentation Pipeline Segmentation Pipeline was developed

Musket ML 52 Dec 12, 2022
HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis Jungil Kong, Jaehyeon Kim, Jaekyoung Bae In our paper, we p

Rishikesh (ऋषिकेश) 31 Dec 08, 2022