Skip to content
View shangeth's full-sized avatar
🏠
Working from home
🏠
Working from home

Organizations

@SforAiDl

Block or report shangeth

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
shangeth/README.md

Hi there, I'm Shangeth 👋

Researcher, Developer!

  • Senior Machine Learning Research Scientist at Anyreach AI
  • Previously,
  • Research Interests 🤓
    • Turn-Taking
    • Multi-Modal LLM(Speech)
    • Spoken Dialogue Systems
    • Speech Representations
    • Unsupervised/Semi-Supervised Representation Learning
    • Deep Reinforcement Learning

Check out my recent research paper - "DualTurn: Learning Turn-Taking from Dual-Channel Generative Speech Pretraining"

Connect with me:

mail me shangeth.com twitter | Twitter linkedin | LinkedIn Google Scholar | Google Scholar orcid | ORCiD

Pinned Loading

  1. skit-ai/SpeechLLM skit-ai/SpeechLLM Public

    This repository contains the training, inference, evaluation code for SpeechLLM models and details about the model releases on huggingface.

    Python 137 14

  2. wren wren Public

    Wren: A Family of Small Open-Weight Models for Unified Speech-Text Modelling

  3. wavencoder wavencoder Public

    WavEncoder is a Python library for encoding audio signals, transforms for audio augmentation, and training audio classification models with PyTorch backend.

    Python 92 14

  4. AccentRecognition AccentRecognition Public

    Identification of accent of an english speaker with their speech signal.

    Python 10

  5. SpeakerProfiling SpeakerProfiling Public

    Estimating the Age, Height, and Gender of a speaker with their speech signal. https://arxiv.org/pdf/2110.13653.pdf

    Python 68 22

  6. skit-ai/slu-prosody skit-ai/slu-prosody Public

    Code repository for the paper "Improving End-to-End SLU performance with Prosodic Attention and Distillation" accepted at Interspeech 2023.

    Jupyter Notebook 27 3