- Slides: Upsampling artifacts in neural audio synthesis. Deep Learning Barelona Symposium. December 2021.
- Poster: Multichannel-based learning for audio object extraction. Deep Learning Barelona Symposium. December 2021.
- Slides: Research at Dolby, my personal journey. ISMIR Industry Presentations. November 2021.
- Slides: Ethics and aesthetics: towards building an artistic discourse around music AI. Exploring connections between AI and Music Workshop by Sonar & UPC. May 2021.
- Slides: Upsampling artifacts in neural audio synthesis. London Audio & Music AI Meetup. December 2020. Links: paper, video.
- Slides: Tutorial on Recurrent Neural Networks. Master in Sound and Music Computing Class. Music Technology Group, UPF, Barcelona. January 2020.
- Thesis Defense, slides: Deep neural networks for music and audio tagging. University Pompeu Fabra, Barcelona. November 2019.
- Slides: Waveform-based deep learning research at Dolby. Industry meetup at ISMIR conference, Delft. November 2019.
- Slides: Waveform-based music processing with deep learning. Tutorial at ISMIR conference, Delft. November 2019.
- Poster: MusiCNN: pre-trained convolutional neural networks for music audio tagging. Late-breaking/demo session in ISMIR conference, Delft. November 2019.
- Slides: End-to-end music source separation: is it possible in the waveform domain? BCN.ai, MoviStar Centre (Barcelona). October 2019.
- Poster: End-to-end music source separation: is it possible in the waveform domain? Interspeech, Graz (Austria). September 2019.
- Updated Slides: Deep learning architectures for music audio classification: a personal (re)view. Invited talk at Adobe Research, San Francisco. August 2019.
- Slides: Training neural audio classifiers with few data. ICASSP, Brighton (UK). May 2019.
- Poster: End-to-end learning for music audio tagging at scale. ISMIR conference, Paris. September 2018.
- Slides: Randomly weighted CNNs for (music) audio classification. Invited talk in the Centre for Digital Music (C4DM) @ Queen Mary Universtity of London. May 2018.
-
Slides: Deep learning architectures for music audio classification: a personal (re)view. Deep Learning for Speech and Language Winter Seminar @ UPC, Barcelona. January 2018.
- Poster: End-to-end learning for music audio tagging at scale. ISMIR late-breaking/demo session, China. October 2017.
- Poster: Score-informed syllable segmentation for a capella singing voice with convolutional neural networks. ISMIR conference, China. October 2017.
- Poster: Audio to score matching by combining phonetic and duration information. ISMIR conference, China. October 2017.
- Poster: Freesound Datasets: A platform for the creation of open audio datasets. ISMIR conference, China. October 2017.
- Slides: A Wavenet for Speech Denoising. Pandora and Dolby, Bay Area. Summer 2017.
- Poster: Designing efficient architectures for modeling temporal features with CNNs. ICASSP, New Orleans. March 2017.
- Slides: Deep learning for music data processing – a personal (re)view of the state-of-the-art. Deep Learning for Speech and Language, Winter Seminar @ UPC, Barcelona. January 2017.
- Slides: Tutorial on Recurrent Neural Networks. Deep Learning Study Group, DTIC, UPF, Barcelona. January 2017.
- Poster: Towards a grounded deep learning paradigm for music modeling. Seminar on music knowledge extraction using machine learning, co-located with NIPS. Barcelona, December 2016.
- Slides: Experimenting with musically motivated CNNs. 14th International Workshop on Content-based Multimedia Indexing (CBMI16). Bucharest, Romania. June 2016.
- Slides: State-of-the-art in deep learning-MIR. Music and Sound Computing MSc: Journal Club. Music Technology Group, UPF, Barcelona. November 2015.
- Slides: Source separation introduction with FASST-NMF. Internal talk. DHZ-Hannover Medical School, Germany. May 2015.