Subject: [AUDITORY] Announcing OpenL3 v0.3.0: now supporting audio AND image embeddings (and more!) From: Jason Cramer <jtc440@xxxxxxxx> Date: Tue, 28 Jan 2020 10:33:58 -0500 List-Archive:<http://lists.mcgill.ca/scripts/wa.exe?LIST=AUDITORY>--000000000000883f9c059d34f46c Content-Type: text/plain; charset="UTF-8" (Apologies for cross-posting) Hello everyone! We're excited to announce the release of version 0.3.0 of *OpenL3 <https://github.com/marl/openl3>*, an open-source deep audio embedding based on the self-supervised L3-Net. As a reminder, OpenL3 is an improved version of L3-Net <https://deepmind.com/research/publications/look-listen-and-learn/>, and outperforms VGGish and SoundNet (and the original L3-Net) on several sound recognition tasks. *In this latest version, we have added functionality extracting image embeddings, processing video files, and batch processing.* OpenL3 is open source and readily available for everyone to use: if you have TensorFlow installed just run *pip install openl3* and you're good to go! Full details are provided in our paper: Look, Listen and Learn More: Design Choices for Deep Audio Embeddings J. Cramer, H.-H. Wu, J. Salamon, and J. P. Bello. IEEE Int. Conf. on Acoustics, Speech and Signal Proc. (ICASSP), pp 3852-3856, Brighton, UK, May 2019. Cheers, Jason Cramer, Ho-Hsiang Wu, Justin Salamon and Juan Pablo Bello. --000000000000883f9c059d34f46c Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable <div dir=3D"ltr">(Apologies for cross-posting)<br><br>Hello everyone!<br><b= r>We're excited to announce the release of version 0.3.0 of <b><a href= =3D"https://github.com/marl/openl3">OpenL3</a></b>, an open-source deep aud= io embedding based on the self-supervised L3-Net. As a reminder, OpenL3 is = an improved version of <a href=3D"https://deepmind.com/research/publication= s/look-listen-and-learn/">L3-Net</a>, and outperforms VGGish and SoundNet (= and the original L3-Net) on several sound recognition tasks.<br><br><b>In t= his latest version, we have added functionality extracting image embeddings= , processing video files, and batch processing.</b> OpenL3 is open source a= nd readily available for everyone to use: if you have TensorFlow installed = just run <b><span style=3D"font-family:monospace">pip install openl3</span>= </b> and you're good to go!<br><br>Full details are provided in our pap= er:<br><br>Look, Listen and Learn More: Design Choices for Deep Audio Embed= dings<br>J. Cramer, H.-H. Wu, J. Salamon, and J. P. Bello.<br>IEEE Int. Con= f. on Acoustics, Speech and Signal Proc. (ICASSP), pp 3852-3856, Brighton, = UK, May 2019.<br><br>Cheers,<br>Jason Cramer, Ho-Hsiang Wu, Justin Salamon = and Juan Pablo Bello.</div> --000000000000883f9c059d34f46c--