DemisEom / SpecAugment
A Implementation of SpecAugment with Tensorflow & Pytorch, introduced by Google Brain
β648Updated 3 years ago
Alternatives and similar repositories for SpecAugment:
Users that are interested in SpecAugment are comparing it to the libraries listed below
- π¦ A Pytorch implementation of GoogleBrain's SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitionβ494Updated 3 years ago
- End-to-end ASR/LM implementation with PyTorchβ596Updated 3 years ago
- Deep speaker embeddings in PyTorch, including x-vectors. Code used in this work: https://arxiv.org/abs/2007.16196β314Updated 4 years ago
- PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.β583Updated 3 years ago
- A library for speech data augmentation in time-domainβ656Updated 3 years ago
- A PyTorch implementation of Listen, Attend and Spell (LAS), an End-to-End ASR framework.β200Updated 6 years ago
- Python functions for reading kaldi data formats. Useful for rapid prototyping with python.β376Updated last year
- Problem Agnostic Speech Encoderβ440Updated last year
- Utterance-level Aggregation For Speaker Recognition In The Wildβ368Updated 2 years ago
- [InterSpeech 2020] "AutoSpeech: Neural Architecture Search for Speaker Recognition" by Shaojin Ding*, Tianlong Chen*, Xinyu Gong, Weiwei β¦β208Updated 2 years ago
- A PyTorch implementation of Speech Transformer, an End-to-End ASR with Transformer network on Mandarin Chinese.β787Updated 2 years ago
- Speech Enhancement Generative Adversarial Network in PyTorchβ391Updated last year
- A pure python module for reading and writing kaldi ark filesβ255Updated last month
- End-to-End Automatic Speech Recognition on PyTorchβ298Updated 2 years ago
- UrbanSound classification using Convolutional Recurrent Networks in PyTorchβ389Updated 3 years ago
- Time delay neural network (TDNN) implementation in Pytorch using unfold methodβ202Updated 5 years ago
- Official repository for RawNet, RawNet2, and RawNet3β375Updated last year
- End-to-End Neural Diarizationβ397Updated 3 years ago
- Towards hot directions in industrial end to end speech recognitionβ327Updated 3 years ago
- Speaker embedding(verification and recognition) using Pytorchβ366Updated 4 years ago
- A No-Recurrence Sequence-to-Sequence Model for Speech Recognitionβ375Updated 2 years ago
- SincNet is a neural architecture for efficiently processing raw audio samples.β1,169Updated 3 years ago
- An open source dataset for source separationβ416Updated last year
- A PyTorch implementation of Conv-TasNet described in "TasNet: Surpassing Ideal Time-Frequency Masking for Speech Separation" with Permutaβ¦β700Updated 2 years ago
- Fast audio data augmentation in PyTorch. Inspired by audiomentations. Useful for deep learning.β1,031Updated 3 months ago
- A must-read paper for speech separation based on neural networksβ773Updated 3 years ago
- A Pytorch Implementation of Transducer Model for End-to-End Speech Recognitionβ233Updated 4 years ago
- Simple d-vector based Speaker Recognition (verification and identification) using Pytorchβ211Updated 4 years ago
- Tensorflow implementation of "Generalized End-to-End Loss for Speaker Verification"β368Updated 3 years ago
- Deep Xi: A deep learning approach to a priori SNR estimation implemented in TensorFlow 2/Keras. For speech enhancement and robust ASR.β507Updated 3 years ago