Deep Learning

Uncovering Latent Style Factors for Expressive Speech Synthesis

End-to-End Speech Synthesis

At Google, I am now a member of the team that brought you Tacotron, an end-to-end speech synthesis system that uses neural networks to convert text directly to audio.

Exploring Neural Transducers for End-to-End Speech Recognition

End-to-End Speech Recognition

Baidu’s Deep Speech system does away with the complicated traditional speech recognition pipeline, replacing it instead with a large neural network that is trained in an end-to-end fashion to convert audio into text.

Reducing Bias in Production Speech Models

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Lasagne: First Release

Analyzing Drum Patterns Using Conditional Deep Belief Networks