home.social

#automaticspeechrecognition — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #automaticspeechrecognition, aggregated by home.social.

  1. #Meta has released #Omnilingual #ASR, an open-source #multilingual #automaticspeechrecognition system supporting over 1,600 #languages, with the potential to transcribe more than 5,400 languages. The system, which includes a family of models and a massive speech corpus, is designed to break down language barriers and empower communities worldwide. venturebeat.com/ai/meta-return #tech #media #news

  2. ☎️ Next week is our Feb community call! Taking place 20/02 at 16:00 UTC (8am PST | 11 AM EST | 16:00 GMT | 17:00 CET)

    @pleonard will be leading an expert focus conversation centred on speech-to-text. Come along if you're curious about #speech-to-text or maybe #automaticspeechrecognition or even #largelanguagemodels (or of course our ever present #ai or #ml)

    For full details, including joining link, check out our agenda: docs.google.com/document/d/1n-

    Register your interest & mark yourself as coming!

  3. Hello #ai4lam community! In one week we're hosting our June community call from 15:00 UTC (8 AM California | 11 AM Washington DC | 16:00 UK | 17:00 Paris).

    We'll be hearing from a couple speakers on #automaticspeechrecognition
    1. Javier de la Rosa - introductions to ASR and the National Library of Norway's work with Whisper
    2. Peter Leonard - Transformers based ASR and how it works with archival content

    More details & joining link available on our agenda: docs.google.com/document/d/1Aa
    #ai #glam

  4. Im Panel “Open Humanities in der Filmwissenschaft – zwischen Wunsch und Wirklichkeit” diskutieren @josidie, Ralph Ewerth, Thomas Scherer, Teodora Vuković, Ariadne Baresch, @SarahMaiDang und @ghowa über Open Access, alternative Publikationsformen, Nachnutzbarkeit von Software, Infrastrukturen und die Anwendung von #ComputerVision und #AutomaticSpeechRecognition in der und für die Filmwissenschaft. #DHd2023 #Filmwissenschaft #DH

  5. #introduction My name is Matt, and I am a phonetician and postdoc in the Department of Linguistics at the #UniversityOfWashington. I am also the currently the acting director of the UW Phonetics Lab.

    In #phonetics, my research focuses on bringing more acoustic information into #SpokenWordRecognition and #LexicalModeling. I am also interested in #SpeechTechnology such as #ForcedAlignment and #AutomaticSpeechRecognition methods.