SLT2022 Call For Papers is out! Visit the workshop website and download the call for papers. slt2022.org Watch this space for the opening of the submission system and other exciting announcements! See you in Qatar in January 2023! #callforpapers #SLT2022

OPT-175b: Open Pre-Trained language model with 175 billion paramaters is now available to the research community. Blog post: ai.facebook.com/blog/democrati… Paper: arxiv.org/abs/2205.01068 Code + small pre-trained models: github.com/facebookresear… (using OPT-175b requires a registration)

The deadline for Full Paper Submission is approaching fast! 15th of July 2022. The submission instructions are available here: slt2022.org/paper-submissi… #SpeechProc #SLT2022 #deadline #callforpapers

Exciting Hackathon Announcement: Have you ever asked yourself how your smartphone recognizes what you say and who you are? How do machines recognize different languages? Interested? Apply/register here: forms.gle/a2droYbD4qset8… The deadline for registration is November 4th, 2022.

JSALT2022 Esperanto by Anthony Larcher JHU CLSP youtube.com/watch?v=41UzPq… clsp.jhu.edu/speech-transla… #speechproc

JSALT2022 Opening Day Presentation: Multilingual and Code-Switching Speech Recognition by @ahmaksod JHU CLSP youtube.com/watch?v=QjYJkY… clsp.jhu.edu/multilingual-a… #speechproc

JSALT2022 Opening Day Presentation: Leveraging Pre-training Models for Speech Processing JSALT 2022 - pre-training team by Hung-yi Lee (李宏毅) JHU CLSP youtube.com/watch?v=lx8mxE… clsp.jhu.edu/leveraging-pre… #speechproc

JSALT2022 Opening Day Presentations Introduction by Sanjeev Khudanpur JHU CLSP youtube.com/watch?v=p1peJh… clsp.jhu.edu/2022-eighth-fr… #speechproc

Have you ever considered becoming a student volunteer? We are looking for student volunteers to work with us in Incheon - we have an interesting offer for you that combines your learning experience with support for the registration! bit.ly/3yhQcHT

Last chance! Submit a paper for #SLT2022 by July 15, 2022. Learn more about all topics and submission guidelines here: slt2022.org/paper-submissi… SLT 2024 #speechProc

Have you wondered about the magic behind generative AI art tools like DALL·E and Midjourney? Seeing the outputs is fun, and learning the algorithms can be even more rewarding. Today we look at 4 popular Machine Learning models — Autoencoder, Transformer, Diffusion Model, and GAN.

Hi all, SLT'22 will organize a hackathon event. Please check slt2022.org/hackathon.php The application deadline is Sep. 30th! SLT 2024

First speech conference in the region. Don't miss it out. 2-days #speechproc hackathon and Technologies for the spoken languages of the world. Join in person and make SLT2022 success! slt2022.org/registration.p…

Dialectal intrasentential code-switching Arabic-English(/French) ASR test set is now available for download from Arabic Speech Portal. Check Data: arabicspeech.org/escwa/ and let us know what you think about it. #speechProc #dialectalArabicSpeech QCRI ALT Group QCRI

Remind us with Roger K Moore's talk: Are we nearly there yet? Looking forward to Sanjeev and panelist discussion. JHU CLSP SLT 2024 #speechproc

Excited to share that QASR TTS corpus/code/demo is available here: arabicspeech.org/qasr_tts/ More resources are coming soon!

📢The largest 2,000 hours multi-layer annotated corpus QASR is available @ arabicspeech.org/qasr/ QASR is suitable for ASR, dialect ID, punctuation, speaker ID-linking, and potentially other NLP modules for spoken data. #nlproc #speechproc #Arabic #AI QCRI | معهد قطر لبحوث الحوسبة QCRI ALT Group

📢🗣️The first Arabic TTS Challenge: QASR TTS 1.0 is open for registration! Part of #ASRU2023, 2 tracks: 1: 1 hour of clean and revised data 2: 10 hours of semi-labeled Broadcast data. Build your own Arabic News Anchor. 👉arabicspeech.org/qasr-challenge/ #speechproc #tts #GenerativeAI

📢🗣️The first Arabic TTS challenge: QASR TTS 1.0 is open for registration! Part of #ASRU2023, Two tracks: 1⃣ 1 hour of clean and revised data. 2⃣ 10 hours of automatically labeled data. Build your own Arabic anchor speaker! 👉arabicspeech.org/qasr-challenge/ #speechproc #tts #GenerativeAI

Now that WAVLab | @CarnegieMellon has created an open-science alternative to Whisper (called OWSM), I hope researchers building/analyzing whisper-based systems switch to OWSM instead!