adhishthite / sound-mnist
A Convolutional Neural Network to identify spoken digits.
☆50Updated 2 years ago
Related projects ⓘ
Alternatives and complementary repositories for sound-mnist
- A neural attention model for speech command recognition☆180Updated last year
- Identifying people from small audio fragments☆169Updated 4 years ago
- This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and dec…☆37Updated 6 years ago
- Music genre classification using Convolutional Neural Networks on Spectrograms in PyTorch☆38Updated 5 years ago
- Keras (tensorflow) implementation of SincNet (Mirco Ravanelli, Yoshua Bengio - https://github.com/mravanelli/SincNet)☆72Updated 3 years ago
- ESC: Dataset for Environmental Sound Classification - paper replication data☆76Updated 6 years ago
- TiFGAN: Time Frequency Generative Adversarial Networks☆114Updated 2 years ago
- Utils and data sets for audio and PyTorch☆83Updated 2 years ago
- A walkthrough of how to make spectrograms in python that are customized for human speech research.☆36Updated 9 months ago
- A free audio dataset of spoken digits. An audio version of MNIST.☆626Updated 6 months ago
- A light weight neural speaker embeddings extraction based on Kaldi and PyTorch.☆137Updated 4 years ago
- End-to-End Speech Recognition Using Tensorflow☆41Updated last year
- A simple audio feature extraction library☆79Updated 5 years ago
- ☆129Updated 2 months ago
- 🎧 Automatic Speech Recognition: DeepSpeech & Seq2Seq (TensorFlow)☆223Updated 4 years ago
- keras project for audio deep learning☆40Updated 6 years ago
- Authors' implementation of DeepSpeech Distances.☆128Updated 4 years ago
- A list of publically available audio data that anyone can download for ASR or other speech activities☆200Updated 3 years ago
- Built a deep neural network that functions as part of an end-to-end automatic speech recognition (ASR) pipeline.☆48Updated 5 years ago
- Tensorflow - Very Deep Convolutional Neural Networks For Raw Waveforms - https://arxiv.org/pdf/1610.00087.pdf☆73Updated 3 years ago
- ☆348Updated 8 months ago
- A pytroch implementation of the GAN-TTS: HIGH FIDELITY SPEECH SYNTHESIS WITH ADVERSARIAL NETWORKS☆229Updated 4 years ago
- Augmented Audio Data Generator for 1D-Convolutional Neural Networks☆49Updated 3 years ago
- openXBOW - the Passau Open-Source Crossmodal Bag-of-Words Toolkit☆81Updated 3 years ago
- Speech Recognition model based off of FAIR research paper built using Pytorch.☆82Updated 5 years ago
- Problem Agnostic Speech Encoder☆439Updated last year
- It uses GMM to train a gender detector model. The testing has been done on subset of Google's AudioSet corpus.☆19Updated 7 years ago
- ☆151Updated 3 years ago
- Speech Commands Recognition in PyTorch☆34Updated 6 years ago