Voice2Series-Reprogramming
Acoustic model reprogramming
An approach to reprogramming acoustic models for time series classification using differential mel-spectrograms and adversarial training
ICML 21 - Voice2Series: Adversarial Reprogramming Acoustic Models for Time Series Classification
70 stars
3 watching
12 forks
Language: TypeScript
last commit: over 1 year ago deep-learningmachine-learningspeech-processingtime-seriestransfer-learning
Related projects:
| Repository | Description | Stars |
|---|---|---|
 dodohow1011/speechadvreprogram | Developing low-resource speech command recognition systems using adversarial reprogramming and transfer learning | 18 |
 yunyuntsai/black-box-adversarial-reprogramming | An approach to adapt machine learning models using scarce data and limited resources by modifying their internal workings without changing the model's original architecture or training data. | 37 |
 paarthneekhara/multimodal_rerprogramming | Cross-modal Adversarial Reprogramming enables retraining of image models on text classification tasks | 11 |
| paarthneekhara/rnn_adversarial_reprogramming | Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs. | 6 |
 prinsphield/adversarial_reprogramming | This project enables reprogramming of pre-trained neural networks to work on new tasks by fine-tuning them on smaller datasets. | 33 |
 matlab-deep-learning/wav2vec-2.0 | Enables speech-to-text transcription using a pre-trained neural network model in MATLAB. | 7 |
 keunwoochoi/auralisation | Reconstructs audio features learned by convolutional neural networks into audible sounds | 42 |
 balavenkatesh3322/audio-pretrained-model | A collection of pre-trained audio and speech models for various applications | 183 |
 yuangongnd/ltu | An audio and speech large language model implementation with pre-trained models, datasets, and inference options | 396 |
 cauchyturing/ucr_time_series_classification_deep_learning_baseline | Developing and evaluating deep learning models for time series classification with a focus on interpretability and deployability. | 682 |
 kinwaicheuk/nnaudio | An audio processing toolkit using PyTorch convolutional neural networks to generate spectrograms from raw audio data | 1,036 |
 hfawaz/dl-4-tsc | This project provides a framework for evaluating and comparing different deep learning architectures for time series classification tasks. | 1,576 |
 tiger-ai-lab/uniir | Trains and evaluates a universal multimodal retrieval model to perform various information retrieval tasks. | 114 |
 awni/speech | A PyTorch implementation of end-to-end speech recognition models. | 756 |
 husainzafar/transferlearningtutorial | Applying transfer learning to retrain Inception model on custom dataset | 93 |