ag027592

Unified-Spectral-Prosodic-SE

audtorch

Utils and data sets for audio and PyTorch

AVUC

Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.

bottleneck

Code for the paper: "On the Bottleneck of Graph Neural Networks and Its Practical Implications"

calibrated-quantile-uq

Training quantile models

CLUE

中文语言理解基准测评 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

CMU-MultimodalSDK

CMU MultimodalSDK is a machine learning platform for development of advanced multimodal models as well as easily accessing and processing multimodal datasets.

Compact_SER

coRNN

Official code for Coupled Oscillatory RNN (ICLR 2021, Oral)

fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Few_Shot_Distribution_Calibration

[ICLR2021 Oral] Free Lunch for Few-Shot Learning: Distribution Calibration

GGAN

graph_emotion_recognition

graph_neural_net

Expressive Power of Invariant and Equivaraint Graph Neural Networks (ICLR 2021)

GraphMask

HGSL

Source code of AAAI21-Heterogeneous Graph Structure Learning for Graph Neural Networks

L3Net

Graph Convolution with Low-rank Learnable Local Filters (ICLR 2021)

labelshiftexperiments

Label shift experiments

MAVEN-dataset

Source code and dataset for EMNLP 2020 paper "MAVEN: A Massive General Domain Event Detection Dataset".

ML-GCN

PyTorch implementation of Multi-Label Image Recognition with Graph Convolutional Networks, CVPR 2019.

MMESGN

Transformer-based Label Set Generation for Multi-modal Multi-label Emotion Detection

multilingual

Automatically Identifying Language Family from Acoustic Examples in Low Resource Scenarios

omnizart

Omniscient Mozart, being able to transcribe everything in the music, including vocal, drum, chord, beat, instruments, and more.

OpenCC

Conversion between Traditional and Simplified Chinese

Self-Supervised-Speech-Pretraining-and-Representation-Learning

Official implementation of the S3PRL toolkit: self-supervised pre-training of Mockingjay, TERA, AALBERT, APC, and more to come. With easy-to-use standard downstream evaluation scripts including phone classification, speaker recognition, and ASR. (All in Pytorch)

SkipConvNet

Speech Dereverberation using Fully Convolutional Networks

stocksight

Stock market analyzer and predictor using Elasticsearch, Twitter, News headlines and Python natural language processing and sentiment analysis

TCN

Sequence modeling benchmarks and temporal convolutional networks

TransUNet

This repository includes the official project of TransUNet, presented in our paper: TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation.

wavenet_autoencoders

WaveNet auto-ancoders for ZeroSpeech challenge 2020