Skip to content

@MLSpeech Speech, Language, and AI Lab

Change the repository type filter

All

    Repositories list

    41 repositories

    • ssl_diarization

      Public
      Self-supervised Speaker Diarization Interspeech 2022 Implementation
      Python
      •0•8•0•0•Updated Feb 2, 2026Feb 2, 2026

    • coupled-diffusion

      Public
      Python
      •1•0•0•0•Updated Jan 27, 2026Jan 27, 2026

    • HyperSpotter

      Public
      Python
      •
      MIT License
      •1•0•0•0•Updated Sep 12, 2025Sep 12, 2025

    • CarelessWhisper-Streaming

      Public
      Causal streaming adaptation of OpenAI Whisper for real-time transcription on small audio chunks.
      Python
      •
      Other
      •13•0•0•0•Updated Aug 21, 2025Aug 21, 2025

    • StructED

      Public
      Risk Minimization Algorithms in Structured Prediction
      Java
      •
      Other
      •2•0•0•0•Updated Jun 13, 2025Jun 13, 2025

    • DIFFAR

      Public
      Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
      Python
      •
      MIT License
      •3•0•0•0•Updated Jun 7, 2025Jun 7, 2025

    • percept_sim

      Public
      Jupyter Notebook
      •2•0•0•0•Updated Jun 7, 2025Jun 7, 2025

    • DeepFormants

      Public
      Formant Tracking & Estimation
      Python
      •
      MIT License
      •17•82•6•2•Updated Dec 15, 2024Dec 15, 2024

    • WhisperDenoiser

      Public
      Python
      •0•4•0•0•Updated Oct 6, 2024Oct 6, 2024

    • DDKtor

      Public
      Python
      •
      MIT License
      •1•2•0•0•Updated Aug 8, 2024Aug 8, 2024

    • scaler_gan

      Public
      Python
      •3•6•1•1•Updated Jul 27, 2024Jul 27, 2024

    • Whisper_denoiser

      Public
      0•0•0•0•Updated Jun 9, 2024Jun 9, 2024

    • FormantsTracker

      Public
      Python
      •
      MIT License
      •6•15•1•1•Updated Apr 1, 2024Apr 1, 2024

    • Dr.VOT

      Public
      Dr.VOT is an a software package for automatic measurement of voice onset time (VOT).
      Python
      •10•32•1•2•Updated Jul 25, 2023Jul 25, 2023

    • GradSeg

      Public
      Python
      •
      MIT License
      •3•4•1•0•Updated Mar 13, 2023Mar 13, 2023

    • .github

      Public
      0•0•0•0•Updated Dec 31, 2022Dec 31, 2022

    • DeepFry

      Public
      Python
      •
      MIT License
      •7•0•0•0•Updated Dec 8, 2022Dec 8, 2022

    • PiMOD

      Public
      Pitch Estimation by Multiple Octave Decoders
      Python
      •
      MIT License
      •1•0•0•0•Updated Oct 30, 2022Oct 30, 2022

    • DSegKNN

      Public
      Python
      •2•1•0•0•Updated Oct 25, 2022Oct 25, 2022

    • speech_yolo

      Public
      SpeechYOLO Interspeech 2019
      Python
      •
      MIT License
      •12•46•3•0•Updated Aug 16, 2022Aug 16, 2022

    • UnsupSeg

      Public
      Self-Supervised Contrastive Learning for Unsupervised Phoneme Segmentation (INTERSPEECH 2020)
      Python
      •
      MIT License
      •32•0•0•0•Updated Aug 5, 2022Aug 5, 2022

    • CRP

      Public
      Training with constant perturbations against adversarial attacks.
      Python
      •0•0•0•0•Updated Feb 17, 2021Feb 17, 2021

    • HideAndSpeak

      Public
      Python
      •12•0•0•0•Updated Jan 17, 2021Jan 17, 2021

    • FixedClassificationLayer

      Public
      Python
      •0•0•0•0•Updated Nov 22, 2020Nov 22, 2020

    • WatermarkVerification

      Public
      TeX
      •1•0•0•0•Updated Apr 12, 2020Apr 12, 2020

    • MLSpeech.github.io

      Public
      Machine learning-based tools for fine grained phonetic measurements
      HTML
      •
      Other
      •0•0•0•0•Updated Nov 24, 2019Nov 24, 2019

    • Image-Captioning

      Public
      This project implements the paper: "Show, Attend and Tell: Neural Image Caption Generation with Visual Attention"
      Python
      •0•1•0•0•Updated Jul 8, 2019Jul 8, 2019

    • semantic_OOD

      Public
      0•0•4•0•Updated Nov 3, 2018Nov 3, 2018

    • WatermarkNN

      Public
      Watermarking Deep Neural Networks (USENIX 2018)
      Python
      •33•1•0•0•Updated Oct 8, 2018Oct 8, 2018

    • AutoPreaspiration

      Public
      A software package for automatic extraction of pre-aspiration from speech segments in audio files, using a trainable algorithm.
      C++
      •
      GNU Lesser General Public License v3.0
      •1•2•0•0•Updated Jun 24, 2017Jun 24, 2017
    ProTip! When viewing an organization's repositories, you can use the props. filter to filter by custom property.