4 papers
Hybrid Autoregressive Transducer (hat)
Ehsan Variani, David Rybach, Cyril Allauzen +1
This paper proposes and evaluates the hybrid autoregressive transducer (HAT) model, a time-synchronous encoderdecoder model that preserves the modularity of conventional automatic…
A Density Ratio Approach to Language Model Fusion in End-To-End Automatic Speech Recognition
Erik McDermott, Hasim Sak, Ehsan Variani
This article describes a density ratio approach to integrating external Language Models (LMs) into end-to-end models for Automatic Speech Recognition (ASR). Applied to a Recurrent…
WEST: Word Encoded Sequence Transducers
Ehsan Variani, Ananda Theertha Suresh, Mitchel Weintraub
Most of the parameters in large vocabulary models are used in embedding layer to map categorical features to vectors and in softmax layer for classification weights. This is a bott…
Non-Adaptive Policies for 20 Questions Target Localization
Ehsan Variani, Kamel Lahouel, Avner Bar-Hen +1
The problem of target localization with noise is addressed. The target is a sample from a continuous random variable with known distribution and the goal is to locate it with minim…