Code, Dataset, and Pretrained Models for Audio and Speech Large Language Model "Listen, Think, and Understand".

Code and Pretrained Models for ICLR 2023 Paper "Contrastive Audio-Visual Masked Autoencoder".

Code and Pretrained Models for Interspeech 2023 Paper "Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong Audio Event Taggers"

Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".

Code for the Interspeech 2021 paper "AST: Audio Spectrogram Transformer".

Code for the IEEE Signal Processing Letters 2022 paper "UAVM: Towards Unifying Audio and Visual Models".

Code for the ICASSP 2022 paper "Transformer-Based Multi-Aspect Multi-Granularity Non-native English Speaker Pronunciation Assessment".

Dataset and baseline code for the VocalSound dataset (ICASSP2022).

Code for the AAAI 2022 paper "SSAST: Self-Supervised Audio Spectrogram Transformer".

Code for SPL paper "Detecting Replay Attacks Using Multi-Channel Audio: A Neural Network-Based Method"

kaldi name convention note

Code for IJCAI 2019 paper "Real-time Adversarial Attack".

ReMASC: Realistic Replay Attack Corpus for Voice Controlled Systems

Simple Python script to compute equal error rate (EER) for machine learning model evaluation.