Florian Schmid

CD-MSC. BioDCASE 2026 Challenge Baseline for Cross-Domain Mosquito Species Classification

dcase2026_task1_baseline. Python

DESED_task. Domestic environment sound event detection task

pruning-algorithms-research-project. Python

dcase25task4. Python

sed-hsmm. Onset-and-Offset-Aware Sound Event Detection

tacos. Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining

TracheoSpeech_ASR. In this repository we provide the codes and procedures which we used to develop an ASR system for a patient with a severe speech impediment caused by permanent tracheal stoma and/or neurological damage.

dcase2025_task4_baseline. Python

EfficientSED. Python

audio_understanding. Python

QBV-Browser. QBV Browser

sebbs. Prediction of sound event bounding boxes (SEBBs)

Audio_Tagging_Jimmy. This project is for "Practical Work in AI"

EfficientAT. This repository aims at providing efficient CNNs for Audio Tagging. We provide AudioSet pre-trained models ready for downstream training and extraction of audio embeddings.

cpjku_dcase24. Python

PretrainedSED. Python

DCASE24_Task1. Python

audiossl. A library built for easier audio self-supervised training, downstream tasks evaluation

beat_this. Accurate and general beat tracker

QBV. This repository provides the code for "Improving Query-by-Vocal Imitation with Contrastive Learning and Audio Pretraining", presented at DCASE 2024. The paper addresses the challenge of audio retrieval using vocal imitations as queries, proposing a dual encoder architecture that leverages pretrained CNNs and an adapted NT-Xent loss for fine-tuning.

easy_dcase_task1. This repository provides an easy way to train your models on the datasets of DCASE task 1.

ATST-SED. This repo includes the official implementations of "Fine-tune the pretrained ATST model for sound event detection".

open-speech-recording. Web application to record speech for an open data set

internet-explorer. Internet Explorer explores the web in a self-supervised manner to progressively find relevant examples that improve performance on a desired target dataset.

descript-audio-codec. State-of-the-art audio codec with 90x compression factor. Supports 44.1kHz, 24kHz, and 16kHz mono/stereo audio.

vector-quantize-pytorch. Vector (and Scalar) Quantization, in Pytorch

AudioSignalProcessingForML. Code and slides of my YouTube series called "Audio Signal Proessing for Machine Learning"

Pytorch-implementation-of-Mobile-Former. Simple implementation of Mobile-Former on Pytorch

practicalwork. Python

cpjku_dcase23. This repository contains the code of the CP JKU submission to DCASE23 Task 1 "Low-complexity Acoustic Scene Classification"

AudioGPT. AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head

Awesome-Deep-Neural-Network-Compression. Summary, Code for Deep Neural Network Quantization

frechet-audio-distance. A lightweight library for Frechet Audio Distance calculation.

torchinfo. View model summaries in PyTorch!

ba3l. Ba3l

Efficient-Deep-Learning. Collection of recent methods on (deep) neural network compression and acceleration.

malach23-pipeline. Jupyter Notebook

DIRAugmentation. Improving Recording Device Generalization using Impulse Response Augmentation

PSL. Source code for ICASSP2022 "Pseudo Strong labels for large scale weakly supervised audio tagging"

ESC-50. ESC-50: Dataset for Environmental Sound Classification

EfficientAT_HEAR. Evaluate EfficientAT models on the Holistic Evaluation of Audio Representations Benchmark.

hear-eval-kit. Evaluation kit for the HEAR Benchmark

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

hearbenchmark.com. HEAR Benchmark website and leaderboard submissions

AudioMAE. This repo hosts the code and models of "Masked Autoencoders that Listen".

audioset_tagging_cnn. Python

cpjku_dcase22. Python

Torch-Pruning. [CVPR 2023] DepGraph: Towards Any Structural Pruning; LLMs, Vision Foundation Models, etc.

da. Pytorch domain adaptation package

passt_hear21. Inference code for PaSST, using the HEAR API.

PaSST. Efficient Training of Audio Transformers with Patchout