Alexandre de Brébisson

2 papers · 2015–2019 · 1 venue · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 📈 Trend Setter

Venues

NeurIPS (2)

Top co-authors

Xavier Bouthillier (1) Rithesh Kumar (1) Jose Sotelo (1) Lucas Gestin (1) Wei Zhen Teoh (1) Kundan Kumar (1) Yoshua Bengio (1) Thibault de Boissiere (1) Aaron C. Courville (1) Pascal Vincent (1)

Research topics

Deep Learning (2) Machine Learning (2) Models (2) Speech & Audio (1) Application Areas (1) Learning Types · Machine Learning (1) Learning Types · Deep Learning (1) Optimization & Theory · Machine Learning (1) Optimization & Theory · Deep Learning (1) Synthesis (1)

Keywords

speech synthesis (1) computational efficiency (1) sparse prediction (1) gradient descent (1) gradient updates (1) generative adversarial network (1) conditional synthesis (1) word embedding (1) neural language model (1) non-autoregressive model (1) waveform synthesis (1) neural network (1) mel-spectrogram inversion (1) hierarchical softmax (1) sparse target (1) large sparse target (1) spherical softmax (1)

Papers

MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis NeurIPS 2019 Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets NeurIPS 2015