Skip to content
@DigitalPhonetics

Speech and Language Technology (SaLT) at the University of Stuttgart

Research institute in the field of speech, natural language processing and machine learning

Pinned Loading

  1. IMS-Toucan IMS-Toucan Public

    Controllable and fast Text-to-Speech for over 7000 languages!

    Python 2.2k 316

  2. VoicePAT VoicePAT Public

    VoicePAT is a modular and efficient toolkit for voice privacy research, with main focus on speaker anonymization.

    Shell 59 6

  3. bloomzmms bloomzmms Public

    Materials for the publication "Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training"

    Python 3

  4. conversational-tree-search conversational-tree-search Public

    Code and Data for Conversational Tree Search: A new task that bridges the gap between FAQ-style information retrieval and task-oriented dialog.

    Python 9

Repositories

Showing 10 of 20 repositories
  • SpeechTokenProbing Public

    Code for the paper “Probing Discrete Speech Tokens of Spoken Language Models” (LREC 2026).

    DigitalPhonetics/SpeechTokenProbing's past year of commit activity
    Python 0 MIT 0 0 0 Updated May 13, 2026
  • IMS-Toucan Public

    Controllable and fast Text-to-Speech for over 7000 languages!

    DigitalPhonetics/IMS-Toucan's past year of commit activity
    Python 2,208 Apache-2.0 316 3 0 Updated Jan 25, 2026
  • diagraph Public

    DIAGRAPH: An open-source graphic interface for dialog flow design

    DigitalPhonetics/diagraph's past year of commit activity
    JavaScript 9 GPL-3.0 4 0 0 Updated Nov 21, 2025
  • voice-privacy-evaluation Public Forked from Voice-Privacy-Challenge/Voice-Privacy-Challenge-2024

    Code of VPC 2024 with extended privacy evaluation options to find overestimated results

    DigitalPhonetics/voice-privacy-evaluation's past year of commit activity
    Python 0 14 0 0 Updated Jul 28, 2025
  • speaker-anonymization Public

    Speaker anonymization pipeline for hiding the identity of the speaker of a recording by changing the voice in it.

    DigitalPhonetics/speaker-anonymization's past year of commit activity
    Shell 105 GPL-3.0 12 1 0 Updated Jul 4, 2025
  • deep-learning-course Public
    DigitalPhonetics/deep-learning-course's past year of commit activity
    Jupyter Notebook 7 2 1 0 Updated Feb 19, 2025
  • conversational-tree-search Public

    Code and Data for Conversational Tree Search: A new task that bridges the gap between FAQ-style information retrieval and task-oriented dialog.

    DigitalPhonetics/conversational-tree-search's past year of commit activity
    Python 9 0 1 0 Updated Feb 5, 2025
  • Intrinsic-Subgraph-Generation-for-VQA Public

    Predicting a subgraph alongside the answer in a graph based VQA model

    DigitalPhonetics/Intrinsic-Subgraph-Generation-for-VQA's past year of commit activity
    Python 9 MIT 1 1 0 Updated Jan 21, 2025
  • hard-negative-captions Public
    DigitalPhonetics/hard-negative-captions's past year of commit activity
    Python 6 0 0 0 Updated Jul 3, 2024
  • bloomzmms Public

    Materials for the publication "Teaching a Multilingual Large Language Model to Understand Multilingual Speech via Multi-Instructional Training"

    DigitalPhonetics/bloomzmms's past year of commit activity
    Python 3 Apache-2.0 0 0 0 Updated Jun 16, 2024
View all repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…