Rezultati pretraživanja
  1. 26. sij

    I am thrilled to announce our paper “Feedback Recurrent AutoEncoder” was accepted at ! collaboration with Yang Yang, and Jon Ryu. . A quick thread.

    Prikaži ovu nit
  2. 27. sij

    Our paper for accurate and scalable music version identification has been accepted to as an oral presentation! The code and the pre-trained models of MOVE are now available! with and paper: code:

  3. 28. sij

    I'm happy to announce our latest work on self-supervised learning for . PASE+ is based on a multi-task approach useful for recognition. It will be presented at . paper: code: @Mila

    Prikaži ovu nit
  4. 25. sij

    Our paper on "SINGING VOICE CONVERSION WITH DISENTANGLED REPRESENTATIONS OF SINGER AND VOCAL TECHNIQUE USING VARIATIONAL AUTOENCODERS" got accepted by a model jointly tackles non-parallel, many-to-many conversion of singer identity and vocal techniques

  5. 27. sij

    Check out our paper accepted for ! It is focused on decomposing speech signals into paralinguistic factor e.g. speaker ID and linguistic factor e.g. phonemes, without utilising transcribed data. Suitable for low-resource and zero-resource ASR

  6. 25. sij

    Our paper titled "Teacher-Student Training for Robust Tacotron-based TTS" is accepted by for oral presentation.🤗Such a nice way to start this weekend! Paper: Speech Samples:

  7. 22. lis 2019.

    For those of you freaking out about paper submission link no longer working, I believe you can still revise submitted papers at . I'm in touch with the chairs to clarify the situation.

  8. 26. sij

    In Omilia we are happy that our paper on end-to-end neural architectures for spoken language understanding has been accepted as oral at ! See you in Barcelona!

  9. 24. sij

    Five papers (including three first author) have been accepted to ! One is our SP Lettres that proposed a simple extension of the well known Griffin-Lim algorithm. Please check it!

  10. 23. ruj 2019.

    Call for Papers - : Deadline = Oct 21. In Barcelona

  11. 25. sij

    Super excited to hear that my paper on confidence scores for black-box speech recognition has been accepted to ! Paper: Code:

  12. 26. sij

    Paper accepted at "Multi-view shape estimation of transparent containers" Pre-print (ArXiv):

  13. 28. sij

    6 papers of were accepted to . You can see the papers: Congrats to all Clova AI authors!

    Prikaži ovu nit
  14. 25. sij

    My paper “Improving the chronological sorting of images through occlusion: A study on the Notre-Dame Cathedral Fire” was accepted to ! This is my first accepted paper as a PhD Student! So happy 🎉🎉🎉 Follow the thread for a summary or check

    Prikaži ovu nit
  15. 24. sij

    Nine papers from our lab. have been accepted to ! Four papers in multi/single-channel source separation, Three papers in speech synthesis and conversion, and two papers in sound field reproduction. Congratulations!

  16. prije 43 minute

    We're happy to announce the DESED dataset (used in task 4)! More information: The dataset was used in two papers accepted to : - - Looking forward to discussing with you in Barcelona!

  17. Submitted a manuscript to . Feeling nervous and excited at the same time...hoyeehhhh

  18. 25. sij

    Calibration error is often used to evaluate uncertainty estimators in neural nets. Our new paper shows calibration is an effective learning objective for deep regression models. Joint work with Link:

  19. 25. sij

    Paper accepted at 🎉

  20. 24. pro 2019.

Čini se da učitavanje traje već neko vrijeme.

Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.