Explore @usc-sail Open Source projects

USC SAIL (@usc-sail)

usc-sail

Stars
293
Global Org. Rank 32,729 (Top 11 %)
Registered over 11 years ago
Most used languages

Python
72.1 %

Jupyter Notebook
9.3 %

MATLAB
9.3 %

C++
2.3 %

TypeScript
2.3 %

TeX
2.3 %

R
2.3 %
Location 🇺🇸 United States
Country Total Rank 21,700
Country Ranking

MATLAB
2,051

TeX
3,376

R
3,404

Python
3,600

C++
4,888

Jupyter Notebook
5,241

fed-multimodal

[KDD 2023] FedMultimodal

gard-adversarial-speaker-id

Adversarial attack and defense strategies for deep speaker recognition systems

barista

Barista is an open-source framework for concurrent speech processing.

mica-deep-mcca

Deep Multiset Canonical Correlation Analysis - An extension of CCA to multiple datasets

mica-race-from-face

Predicting race from faces for movie data

mica-speech-activity-detection

Robust Speech Activity Detection (SAD) in movie audio

mica-subtitle-aligned-movie-sounds

A dataset for Audio-Visual Sound Event Detection in Movies

media-eval-2020

MediaEval 2020: Music Mood Classification

Jupyter Notebook

fed-ser-semi

Semi-supervised Learning for Speech Emotion Recognition On Federated Learning using Multiview Pseudo-Labeling

trust-ser

Trustworthy Speech Emotion Recognition

gen-dmcca

Generalized Deep Multiset Canonical Correlation Analysis for Multiview Learning of Speech Representations

mica-text-script-parser

Code to parse movie screenplays

fed-ser-leakage

peft-ser

PEFT-SER: On the Use of Parameter Efficient Transfer Learning Approaches For Speech Emotion Recognition Using Pre-trained Speech Models (Accepted to 2023 ACII)

mica-screenplay-parser

Movie Screenplay Parser

mica-multimodal-ads

Segment-level autoencoders for multimodal representation

mica-MovieCLIP

This repository contains the codebase for MovieCLIP: Visual Scene Recognition in Movies

tiles-dataset-release

Code accompanying the TILES dataset paper and data release. Data at https://tiles-data.isi.edu.

egocentric-fg-speech-detection

Egocentric Foreground Speech Detection

mica-violence-ratings

Accompanying code for Violence Rating Prediction from Movie Scripts

mica-animation

Unsupervised Discovery of Character Dictionaries in Animation Movies

span_articulatory_strategies

MATLAB tools for extracting articulatory strategies biomarkers from real-time magnetic resonance imaging of the vocal tract

IBdiar

Information Bottleneck based Speaker Diarization system

M3BERT

A music transformer that extracts representations of audio using several hundreds of thousands of music clips. Fine-tuning is done with diverse end-tasks to enrich the pre-trained representations.

mica-riskybehavior-identification

Code companion to Joint Estimation and Analysis of Risk Behavior Ratings in Movie Scripts

mica-gender-from-audio

Gender prediction in movie audio

lorelei-speech-evaluation

The evaluation script for the LORELEI Situation Frames from Speech task.

presentation-template

A USC SAIL presentation template based on mtheme: https://github.com/matze/mtheme

mica-face-clustering

Face clustering for movies using Constraint Propagation Sparse Subspace Clustering (CP-SSC)

span_segmentation

Segmentation tools for real-time magnetic resonance imaging of speech implemented in MATLAB

ccmi-explorecsr

Repository for workshop colabs and coding exercises

Jupyter Notebook

ggs_driving

Segmentation Algorithms for Physiological Time Series

span_contour_processing

MATLAB tools for processing the output of the real-time magnetic resonance image segmentation

speech-emotion-privacy-trust

care-kidsASR

mica-actions-agents-and-patients

Repo for movieSRL and large-scale analysis of character's actions

mica-text-characternetworks

mica-character-attribute-extraction

Character tropes, Forensic Interviews, and Character Attributes

Jupyter Notebook

predicting-human-reported-enjoyment-in-music

Experiments written in Python to determine which models and auditory features best predict human-reported enjoyment in music.

mica-character-coref

Coreference in Movie Scripts

mica-class-pipeline

main code for cLASS pipeline

mupet-subspace-clustering

Code for subspace clustering of mouse ultrasonic vocalizations

Jupyter Notebook

SCMIA-unsupervised-ASD

Repo for SCMIA and GSCMIA

tiles-day-night

tiles-time-series

The repo contains time-series implement for SAIL-TILES projects: preprocessing, segmentation, filtering, clustering, imputation, visualization...