Skip to content
Main Menu
  • Home
  • Seminars
  • People
    • Staff
    • Ph.D. Students
    • Students
    • AUDIAS Alumni
  • Publications
  • Projects & Industry
    • Projects
    • Industry
    • UAM-BioSmartData Chair
  • Evaluations
  • For Students
    • Master’s Thesis Proposals
    • Study Grants and Opportunities
    • Teaching
  • Contact
AUDIAS-UAM
  • Home
  • Seminars
  • People
    • Staff
    • Ph.D. Students
    • Students
    • AUDIAS Alumni
  • Publications
  • Projects & Industry
    • Projects
    • Industry
    • UAM-BioSmartData Chair
  • Evaluations
  • For Students
    • Master’s Thesis Proposals
    • Study Grants and Opportunities
    • Teaching
  • Contact

Day: December 2, 2022

  • Home
  • 2022
  • December
  • 2

Whisper: Robust Speech Recognition via Large-Scale Weak Supervision

December 2, 2022January 16, 2023 daniel

Speaker: Doroteo Torre Toledano. Abstract: Very recently (in Sept 2022) OpenAI has made freely available a speech recognition neural network called Whisper. One of the main differences with respect to the current state of the art is the use of… Read More

AUDIAS Seminars

AUDIAS Seminars

FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition

July 3, 2026

Speaker: William Fernando López Gavilanez. Abstract: Automatic speech recognition (ASR)…

Automatic Classification of Classical Music Composers from Audio Signals

July 2, 2026

Speaker: Sonia Aoi García Shida. Abstract: Automatic composer classification is…

Detection and Grouping of Accents within Rural Spanish

July 2, 2026

Speaker: Koral Tubia. Abstract: Rural Spanish preserves a rich dialectal…

Adapting Speaker Diarization to Code-Switched Medical Conversations: AUDIAS-UAM at the DISPLACE-M Challenge

June 19, 2026

Speaker: Sara Barahona Quirós. Abstract: Speaker diarization of medical conversations…

About AUDIAS

AUDIAS is a solid research group addressing challenging problems in speech, audio and temporal signals from deep foundations in machine learning and signal processing.

Quick Links

  • Home
  • People
  • Publications
  • Industry
  • Evaluations
  • For Students
  • Contact

Highlights

FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition

July 3, 2026

Automatic Classification of Classical Music Composers from Audio Signals

July 2, 2026
Copyright © AUDIAS-UAM All rights reserved.
Education Mind by Axle Themes