desh2608
Ph.D. CS @ JHU | Center for Language and Speech Processing
Johns Hopkins UniversityBaltimore, MD
Pinned Repositories
attention_model_clinical_text
This code implements attention network on top of the CNN used in the paper titled "Relation extraction from clinical texts using domain invariant convolutional neural network" which was accepted in BioNLP at ACL-2016, Berlin, Germany
crnn-relation-classification
Tensorflow implementation of the Convolutional Recurrent Neural Network model with max pooling and attentive pooling, for relation classification on biomedical text.
diarizer
Clustering-based methods for overlapping diarization
dnn-hmm-asr
Hybrid DNN-HMM model for isolated digit recognition
dover-lap
Python package for combining diarization system outputs.
gmm-hmm-asr
Python implementation of simple GMM and HMM models for isolated digit recognition.
gss
A simple package for Guided source separation (GSS)
numerical-linear-algebra
Solutions to exercises in Numerical Linear Algebra by Trefethen and Bau.
pytorch-tdnn
Pypi installable TDNN and TDNN-F layers for PyTorch based acoustic model training
spyder
Simple Python package for fast DER computation
desh2608's Repositories
desh2608/gss
A simple package for Guided source separation (GSS)
desh2608/dover-lap
Python package for combining diarization system outputs.
desh2608/diarizer
Clustering-based methods for overlapping diarization
desh2608/spyder
Simple Python package for fast DER computation
desh2608/css
PyTorch implementation of Continuous Speech Separation
desh2608/desh2608.github.io
Personal homepage for Desh Raj
desh2608/alignment_restricted_transducer
An implementation of AR-RNNT loss as proposed in this paper: https://arxiv.org/abs/2011.03072
desh2608/ai-deadlines
:alarm_clock: AI conference deadline countdowns
desh2608/beamformer
Souden MVDR beamformer on GPU with CuPy
desh2608/cacgmm
GPU-based CACGMM trainer in CuPy
desh2608/kaldialign
Python wrappers for Kaldi Levenshtein's distance and alignment code.
desh2608/lhotse
desh2608/pyannote-audio
Neural building blocks for speaker diarization: speech activity detection, speaker change detection, overlapped speech detection, speaker embedding
desh2608/queue-utils
Utility scripts to submit multi-GPU jobs on CLSP, COE, and MARCC
desh2608/speech-datasets
Various speech datasets made available to the public
desh2608/transducer-loss-benchmarking
desh2608/wpe
Nara-WPE in CuPy for GPU inference
desh2608/espnet
End-to-End Speech Processing Toolkit
desh2608/fast_rnnt
A torch implementation of a recursion which turns out to be useful for RNN-T.
desh2608/gecko
Gecko - A Tool for Effective Annotation of Human Conversations
desh2608/hyperion
Python toolkit for speech processing
desh2608/icefall
desh2608/jsalt2020_simulate
Training data simulation
desh2608/k2
FSA/FST algorithms, intended to (eventually) be interoperable with PyTorch and similar
desh2608/last
A JAX library for building lattice-based speech transducer models
desh2608/plz
Helpers for running native Python functions as qsub jobs on the CLSP grid
desh2608/pytorch-edit-distance
Levenshtein edit-distance on PyTorch and CUDA
desh2608/scikit-learn
scikit-learn: machine learning in Python
desh2608/speechbrain
A PyTorch-based Speech Toolkit
desh2608/streaming_wer
CUDA implementation of Streaming WER metric