Trace norm regularization and faster inference for embedded speech recognition RNNs

no code implementations • ICLR 2018 • Markus Kliegl, Siddharth Goyal, Kexin Zhao, Kavya Srinet, Mohammad Shoeybi

We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR).

speech-recognition Speech Recognition

Reducing Bias in Production Speech Models

no code implementations • 11 May 2017 • Eric Battenberg, Rewon Child, Adam Coates, Christopher Fougner, Yashesh Gaur, Jiaji Huang, Heewoo Jun, Ajay Kannan, Markus Kliegl, Atul Kumar, Hairong Liu, Vinay Rao, Sanjeev Satheesh, David Seetapun, Anuroop Sriram, Zhenyao Zhu

Replacing hand-engineered pipelines with end-to-end deep learning systems has enabled strong results in applications like speech and object recognition.

Object Recognition

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

no code implementations • 15 Mar 2017 • Sercan O. Arik, Markus Kliegl, Rewon Child, Joel Hestness, Andrew Gibiansky, Chris Fougner, Ryan Prenger, Adam Coates

Keyword spotting (KWS) constitutes a major component of human-technology interfaces.

Small-Footprint Keyword Spotting speech-recognition +1