Pinned Repositories
audioset-convnext-inf
Adapting a ConvNeXt model to audio classification on AudioSet
bird_audio_detection_challenge
DenseNets for the detection of singing birds in audio files
ComParE2021_PRS
Pytorch code for the Compare 2021 Interspeech challenge (primates call classification)
dcase19-RCNN-task4
RCNN for the DCASE 2019 sound event detection task
demo-zca
PCA and ZCA whitening on a dummy set of 2-d points
emoMusic
Frame-based regression of valence and arousal in music samples with RNNs
goodness-of-pronunciation-HTK
Phone-level evaluation of L2 speakers (GOP algorithm)
ijcnn19_submission
IJCNN'19: Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection
listen-attend-tell
Audio captioning system based on LAS, used in the DCASE2020 challenge
sglthresh
Surrogate Gradient Learning for estimating multilabel classification thresholds
topel's Repositories
topel/audioset-convnext-inf
Adapting a ConvNeXt model to audio classification on AudioSet
topel/dcase19-RCNN-task4
RCNN for the DCASE 2019 sound event detection task
topel/listen-attend-tell
Audio captioning system based on LAS, used in the DCASE2020 challenge
topel/sglthresh
Surrogate Gradient Learning for estimating multilabel classification thresholds
topel/ComParE2021_PRS
Pytorch code for the Compare 2021 Interspeech challenge (primates call classification)
topel/generativemusicaicourse
Resources for the Generative Music AI Course on The Sound of AI YouTube channel.
topel/IRIT-audio-retrieval-system-dcase2022
Language-based audio retrieval system for DCASE 2022 Task 6b
topel/allosaurus
Allosaurus is a pretrained universal phone recognizer for more than 2000 languages
topel/audio-text_retrieval-xinhaoMei
Implementation of our paper 'On Metric Learning For Audio-Text Cross-Modal Retrieval'
topel/beam_search
Beam search for neural network sequence to sequence (encoder-decoder) models.
topel/dataflowr
code for deep learning courses
topel/Deep-Co-Training-for-Semi-Supervised-Image-Recognition
Unofficial implementation of the paper 'Deep Co-Training for Semi-Supervised Image Recognition'
topel/fairseq_severin
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
topel/FixMatch-pytorch
Unofficial PyTorch implementation of "FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence"
topel/harmonic-oscillator-pinn
Code accompanying my blog post: So, what is a physics-informed neural network?
topel/homemade-machine-learning
š¤ Python examples of popular machine learning algorithms with interactive Jupyter demos and math being explained
topel/INTERSPEECH19_TUTORIAL
Interspeech 2019 tutorial materials
topel/keras-ncp
Code repository of the paper Neural circuit policies enabling auditable autonomy published in Nature Machine Intelligence
topel/machine_learning_basics
Plain python implementations of basic machine learning algorithms
topel/ML1
topel/MMAML-Classification
An official PyTorch implementation of āMultimodal Model-Agnostic Meta-Learning via Task-Aware Modulationā (NeurIPS 2019) by Risto Vuorio*, Shao-Hua Sun*, Hexiang Hu, and Joseph J. Lim
topel/MML-Companion
This is a companion to the āMathematical Foundationsā section of the book, Mathematics for Machine Learning by Marc Deisenroth, Aldo Faisal and Cheng Ong, written in python for Jupyter Notebook.
topel/my-audio-retrieval-dcase2022
Language-based audio retrieval system for DCASE 2022
topel/NoKill_ASR
topel/PaSST
Efficient Training of Audio Transformers with Patchout
topel/pytorch-original-transformer
My implementation of the original transformer model (Vaswani et al.). I've additionally included the playground.py file for visualizing otherwise seemingly hard concepts. Currently included IWSLT pretrained models.
topel/RNN_pytorch_labs
PyTorch practicals on RNNs
topel/sed_vis
Visualization toolbox for Sound Event Detection
topel/SincNet
SincNet is a neural architecture for efficiently processing raw audio samples.
topel/sound_event_detection_dcase2017_task4