12 citations
5 papers
Accelerator-Aware Training for Transducer-Based Speech Recognition
Suhaila M. Shakiah, Rupak Vignesh Swaminathan, Hieu Duy Nguyen +6
Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network a…
Language Model Bootstrapping Using Neural Machine Translation For Conversational Speech Recognition
Surabhi Punjabi, Harish Arsikere, Sri Garimella
Building conversational speech recognition systems for new languages is constrained by the availability of utterances that capture user-device interactions. Data collection is both…
Galaxies of the Universe. I. Grism-Selected Rest-Frame Optical Emission Line Galaxies
William P. Bowman, Gregory R. Zeimann, Robin Ciardullo +6
Euclid, WFIRST, and HETDEX will make emission-line selected galaxies the largest observed constituent in the universe. However, we only have a limited understanding of the…
Pluto Follow On Missions: Background, Rationale, and New Mission Recommendations
Stuart J. Robbins, S. Alan Stern, Richard Binzel +5
The first exploration of Pluto was motivated by (i) the many intriguing aspects of this body, its atmosphere, and its giant impact binary-planet formation; as well as (ii) the scie…
Statistical Model Compression for Small-Footprint Natural Language Understanding
Grant P. Strimel, Kanthashree Mysore Sathyendra, Stanislav Peshterliev
In this paper we investigate statistical model compression applied to natural language understanding (NLU) models. Small-footprint NLU models are important for enabling offline sys…