Sankar Mukherjee's repositories
vocos_finetune
Vocos with finetuning
speech2intent
Speech to text, text to intent. REST API application that can be deployed in cloud.
vits_with_mms
VITS with MMS for TTS
docker-python-ta-lib
A Docker image including Python TA-Lib wrapper and dependencies.
Expressive-Speech-Synthesis
A speech synthesis system with prosody embeddings
Expressive-Speech-Synthesis-Research
do not made public, only for research
sankar-mukherjee.github.io
My Personal Website
academic-kickstart
đź“ť Easily create a beautiful website using Academic, Hugo, and Netlify
Cornell_Birdcall_Identification
identify a wide variety of bird vocalizations in soundscape recordings
ASVspoof2019
ASVspoof 2019: Automatic Speaker Verification Spoofing and Countermeasures Challenge Future horizons in spoofed/fake audio detection
NACA
NEURO-BEHAVIORAL AWARE CONVERSATIONAL AGENT
SpeechConvergence
https://sankar-mukherjee.github.io/SpeechConvergence/
ML_concepts
Repository for simple ml concepts
Conversational-AI
List of softwares
NeuroLip
Investigate the effect of speakers speech and lip movements on listeners perception
CCA_speech_EEG
Neural, Speech and Articulatroy relation using CCA
DecodingEEG2speech
Leveraging deep neural network architecture to find complex speech representation in brain.
BrainSpeechTranslation
Translating brain waves into recognizable speech and vocal tract movements.
gst-tacotron
A tensorflow implementation of the "Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis"
SPIC_EMA
exploring the articulatroy dynamics during speech convergence
EMA_ag500_method_compare
Electromagnetic Articulography (EMA) scripts for comparisons between TAPAD and CALPOS method with AG500 mcal data
Hyperscanning
Dual EEG speech convergence