Krishna's Projects
This repo contains implementation of the paper "Acoustic Scene Analysis With Multihead Self Attention" by Weimin Wang, Weiran Wang, Ming Sun, Chao Wang from Amazon Alexa team
Implementation of the paper "Attention Based Fully Convolutional Network for Speech Emotion Recognition"
Implementation of the paper "Attentive Statistics Pooling for Deep Speaker Embedding" in Pytorch
Audio classification using 1D convolution neural network and attention pooling
Implementation of the paper "BERTphone: Phonetically-aware Encoder Representations for Utterance-level Speaker and Language Recognition"
Implementation of the paper "Broadcasted Residual Learning for Efficient Keyword Spotting"
This repo contains codebase for the paper "Multimodal Transformer for Code-Switching Detection" By Krishna D N
This model implements auto-encoder for speech data using deep convolution neural networks in pytorch
d-vector based language identification using pytorch
This repo will give all the papers related to speaker recognition and speaker verification based on neural networks and short video explanation of each paper.
Deploying Speech Recognition models in Kubernetes
Implementation of the paper "Confidence estimation for attention based sequence to sequence models for speech recognition"
Implementation of the paper "Emotion Identification from raw speech signals using DNNs"
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
Implementation of the paper "Keyword Transformer: A Self-Attention Model for Keyword Spotting"
Language identification for vichar
Implementation of the paper "Listen, Attend and Spell" Paper in Pytorch
learning docker, mongoDB, RESTFUL API
Implementation of the the paper "MLP-Mixer: An all-MLP Architecture for Vision"
This repository will give papers related to techniques for neural network configuration search like evolution strategies, genetic algorithms, bayesian optimization and re-enforcement learning
This repository gives most of the papers which are published in the domain of neural network compression and quantization
Audio processing by using pytorch 1D convolution network
punctuation prediction using BERT
Pytorch implementation of NetVlad including training on Pittsburgh.
Implementation of the paper ": Advanced end-to-end deep neural network using raw waveforms for text-independent speaker verification"
This repo contains implementation of the paper "Siamese X- Vector Reconstruction for domain adapted speaker recognition"