Make beautiful isometric infrastructure diagrams

Collection of works for evaluating (and analyzing) large audio-language models (LALMs)

Open-source unified multimodal model

small audio language model for reasoning

A Conversational Speech Generation Model

Explaining audio differences using language

Unified automatic quality assessment for speech, music, and sound.

Code for the paper: MACE: Leveraging Audio for Evaluating Audio Captioning Systems

Audio Entailment: Deductive Reasoning for Audio Understanding

Awesome speech/audio LLMs, representation learning, and codec models

A simple library for Fréchet Audio Distance (FAD) calculation

PAM is a no-reference audio quality metric for audio generation tasks

Repository for "Training Audio Captioning Models without Audio"

An Audio Language model for Audio Tasks

Tracking states of the arts and recent results (bibliography) on sound tasks.

Web-crawl for "Audio Retrieval with WavText5K and CLAP Training"

Learning audio concepts from natural language supervision

Code repo for "Multi-Task Learning for Interpretable Weakly Labelled Sound Event Detection"

speech enhancement\speech seperation\sound source localization

Self-Supervised Speech Pre-training and Representation Learning Toolkit

Reading list for research topics in Sound AI