Skip to content
View mrpep's full-sized avatar
πŸ€“
πŸ€“

Organizations

@habla-liaa @neurasound

Block or report mrpep

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
mrpep/README.md

Hello, I'm Leonardo Pepino πŸ‘‹

mrpep

Leonardo's Twitter Leonardo's Linkdein Leonardo's Github Leonardo's Google Scholar profile

  • πŸ–₯️ I’m a computer science PhD candidate at Universidad de Buenos Aires πŸ‡¦πŸ‡·.
  • πŸ—£οΈ I'm a member of the speech processing group at the Applied Artificial Intelligence Laboratory 🧠
  • πŸ”Š My main interests are the applications of deep learning to audio signal processing and analysis. I am currently working in audio representation learning and speech emotion recognition.
  • 🎸 In my free time I play guitar, or anything that makes sounds. In my master thesis I developed a fast music source separation system. Check it out!
Leonardo Pepino github stats

Pinned Loading

  1. habla-liaa/encodecmae habla-liaa/encodecmae Public

    Codebase for the paper 'EncodecMAE: Leveraging neural codecs for universal audio representation learning'

    Python 87 4

  2. habla-liaa/ast-pe habla-liaa/ast-pe Public

    Jupyter Notebook 9 2

  3. habla-liaa/ser-with-w2v2 habla-liaa/ser-with-w2v2 Public

    Official implementation of INTERSPEECH 2021 paper 'Emotion Recognition from Speech Using Wav2vec 2.0 Embeddings'

    Jupyter Notebook 126 23

  4. audio-resources audio-resources Public

    A recopilation of audio related resources

    6 4