mravanelli / pytorch_MLP_for_ASR
This code implements a basic MLP for speech recognition. The MLP is trained with pytorch, while feature extraction, alignments, and decoding are performed with Kaldi. The current implementation supports dropout and batch normalization. An example for phoneme recognition using the standard TIMIT dataset is provided.
☆37Updated 6 years ago
Related projects: ⓘ
- Python implementation of pre-processing for End-to-End speech recognition☆69Updated 6 years ago
- Voxceleb1 i-vector based speaker recognition system☆41Updated 6 years ago
- This python code performs an efficient speech reverberation starting from a dataset of close-talking speech signals and a collection of a…☆93Updated 4 years ago
- ☆26Updated 7 years ago
- This is a project on working/resolving the speech separation problem using supervised learning on various training targets, building mach…☆34Updated 7 years ago
- ☆59Updated 3 years ago
- Robust Speech Recognition Using Generative Adversarial Networks (GAN)☆58Updated 4 years ago
- An example directory for running Multi-Task Learning training on Kaldi neural networks. In Kaldi-speak, this is an egs dir for nnet3 trai…☆54Updated 4 years ago
- Speaker embedding(verification and recognition) using Tensorflow with Kaldi☆41Updated 7 years ago
- This repository contains the code and supplementary result for the paper "Unpaired Speech Enhancement by Acoustic and Adversarial Supervi…☆28Updated 4 years ago
- VoxCeleb plugin for pyannote.database☆28Updated 3 years ago
- ☆23Updated this week
- A set of speech feature extraction functions for ASR and speaker identification written in matlab.☆43Updated 7 years ago
- python codes to extract MFCC and FBANK speech features for Kaldi☆62Updated 5 years ago
- ABX and kaldi experiments on speech corpora made easy☆31Updated last year
- Code for the paper "Investigating the effect of residual and highway connections in speech enhancement models"☆11Updated 5 years ago
- Trained speaker embedding deep learning models and evaluation pipelines in pytorch and tesorflow for speaker recognition.☆36Updated 4 years ago
- Keras-based python framework to compute phonological posterior probabilities from audio files☆37Updated last year
- "An Improved Deep Embedding Learning Method for Short Duration Speaker Verification" pytorch implementation☆19Updated 5 years ago
- A Simple Automatic Speech Recognition (ASR) Model in Tensorflow, which only needs to focus on Deep Neural Network. It's easy to test popu…☆19Updated 6 years ago
- Bidirectional dynamic RNN + CTC for phoneme recognition☆44Updated 4 years ago
- Develop speaker recognition model based on i-vector using TIMIT database☆15Updated 5 years ago
- ☆24Updated 5 years ago
- Meta-embeddings are a probabilistic generalization of embeddings in machine learning.☆23Updated 5 years ago
- Speech command recognition with capsule network & various NNs / KWS on Google Speech Command Dataset.☆26Updated 5 years ago
- Gammatone feature for robust speech recognition☆14Updated 8 years ago
- Estimate the number of concurrent speakers from single channel mixtures to crack the "cocktail-party” problem.☆22Updated 4 years ago
- 💬 A list of End-to-End speech recognition, including papers, codes and other materials☆53Updated 5 years ago
- Deep Discriminative Embeddings for Duration Robust Speaker Verification☆19Updated 4 years ago
- Adaptive and Focusing Neural Layers for Multi-Speaker Separation Problem☆49Updated 6 years ago