Awni Y. Hannun

Learn More
Deep neural network acoustic models produce substantial gains in large vocabulary continuous speech recognition systems. Emerging work with rectified linear (ReL) hidden units demonstrates additional gains in final system performance relative to more commonly used sigmoidal nonlinearities. In this work, we explore the use of deep rectifier networks as(More)
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech–two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks, end-to-end learning allows us to handle a diverse variety of speech including noisy environments, accents and different(More)
We present a state-of-the-art speech recognition system developed using end-toend deep learning. Our architecture is significantly simpler than traditional speech systems, which rely on laboriously engineered processing pipelines; these traditional systems also tend to perform poorly when used in noisy environments. In contrast, our system does not need(More)
We present a method to perform first-pass large vocabulary continuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace in HMM-based speech recognition systems, but building such systems is a complex, domain-specific task. Recent work demonstrated the feasibility of discarding the HMM(More)
We apply a machine learning approach to improve noisy acoustic features for robust speech recognition. Specifically, we train a deep, recurrent neural network to map noisecorrupted input features to their corresponding clean versions. We introduce several improvements to previously proposed neural network feature enhancement architectures. The model does(More)
This paper introduces a new technique for mapping Deep Recurrent Neural Networks (RNN) efficiently onto GPUs. We show how it is possible to achieve substantially higher computational throughput at low mini-batch sizes than direct implementations of RNNs based on matrix multiplications. The key to our approach is the use of persistent computational kernels(More)
Understanding architectural choices for deep neural networks (DNNs) is crucial to improving state-of-the-art speech recognition systems. We investigate which aspects of DNN acoustic model design are most important for speech recognition system performance, focusing on feed-forward networks. We study the effects of parameters like model size (number of(More)
The effects of structural analogues of ceramide on rat brain mitochondrial ceramidase (mt-CDase) were investigated. Design of target compounds was mainly based on modifications of the key elements in ceramide and sphingosine, including stereochemistry, the primary and secondary hydroxyl groups, the trans double bond in the sphingosine backbone, and the(More)
Deep learning has dramatically improved the performance of speech recognition systems through learning hierarchies of features optimized for the task at hand. However, true end-toend learning, where features are learned directly from waveforms, has only recently reached the performance of handtailored representations based on the Fourier transform. In this(More)