480 citations · 1.5k across the 24 of their papers we have counts for
10 papers · 1 filter
Investigation of Training Label Error Impact on RNN-T
I-Fan Chen, Brian King, Jasha Droppo
In this paper, we propose an approach to quantitatively analyze impacts of different training label errors to RNN-T based ASR models. The result shows deletion errors are more harm…
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
Gokce Keskin, Minhua Wu, Brian King +5
Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design de…
Listen with Intent: Improving Speech Recognition with Audio-to-Intent Front-End
Swayambhu Nath Ray, Minhua Wu, Anirudh Raju +7
Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly…
SynthASR: Unlocking Synthetic Data for Speech Recognition
Amin Fazel, Wei Yang, Yulan Liu +4
End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model require…
CoDERT: Distilling Encoder Representations with Co-learning for Transducer-based Speech Recognition
Rupak Vignesh Swaminathan, Brian King, Grant P. Strimel +2
We propose a simple yet effective method to compress an RNN-Transducer (RNN-T) through the well-known knowledge distillation paradigm. We show that the transducer's encoder outputs…
Scaling Laws for Acoustic Models
Jasha Droppo, Oguz Elibol
There is a recent trend in machine learning to increase model quality by growing models to sizes previously thought to be unreasonable. Recent work has shown that autoregressive ge…