Skip to content
View koudounasalkis's full-sized avatar

Block or report koudounasalkis

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
koudounasalkis/README.md

Hi there, I am Alkis Koudounas 👋

🇮🇹 🇬🇷


Portfolio Huggingface Hub Twitter LinkedIn Google Scholar

I am a second-year Ph.D. student at Politecnico di Torino and an Applied Research Intern at Amazon AGI Speech Recognition.
I am the teaching assistant for Data Science Lab: Process and Methods and Data Science and Database Technology courses.

  • I am interested in 🔉 Audio, 🗣 Speech, and 🎼 Music Processing, 📝 NLP and Audio-Text Multi-modal Understanding, and 🔬 Trustworthy AI.
  • 🎯 I am mainly working on a joint project with Amazon Alexa AI in Fairness in E2E SLU Models.
  • I am also working on other projects, including 🇮🇹 Italian SLU, 🎶 Music Generation, 🎸🥁 Music Source Separation, ⚖️ Legal AI, 🪐🔭 Exoplanets Atmospheric Parameters Estimation, and many more!
  • 🔭 I’m a space enthusiast and I love taking night-ish photos!
  • 💬 I'm looking to collaborate on the analysis of spoken content, get in touch if you are interested!
  • 📫 Reach me by mail or have a look at my website.

Pinned Loading

  1. ALM-LAB/PACE ALM-LAB/PACE Public

    PACE (Podcast AI for Chapters and Episodes) is a semantic search engine that helps you find the information you need, inter- and intra-podcasts (Project for the AssemblyAI Winter 2022 Hackathon).

    Python 13

  2. ALM-LAB/CALM ALM-LAB/CALM Public

    CALM (Contrastive Alignment of Language and Music) aligns songs with their natural language description using CLIP (Project for the 1st Sound of AI Hackathon).

    Python 8

  3. RiTA-nlp/ITALIC RiTA-nlp/ITALIC Public

    ITALIC: An ITALian Intent Classification Dataset

    Python 11 1

  4. divergence-in-speech-systems divergence-in-speech-systems Public

    Code associated with the paper "Exploring Subgroup Performance in End-to-End Speech Models"

    Jupyter Notebook 6

  5. Audio-Speech-Tutorial Audio-Speech-Tutorial Public

    This repository contains a short introduction on the topic of audio and speech processing -- from basics to applications.

    Jupyter Notebook 18 2

  6. Master-Thesis-Proposal Master-Thesis-Proposal Public

    This repo contains master thesis proposals for Deep Learning applied to Audio and Speech Processing.

    3