AIConfPaper
← Search

Michael Nirschl

2 accepted papers

2018

Modeling Non-Linguistic Contextual Signals in LSTM Language Models Via Domain Adaptation

Min Ma, Shankar Kumar, Fadi Biadsy, Michael Nirschl, Tomas Vykruta, Pedro J. Moreno
ICASSP 2018accepted

Language Models (LMs) for Automatic Speech Recognition (ASR) can benefit from utilizing non-linguistic contextual signals in modeling. Examples of these signals include the geographical location of the user speaking to the system and/or the identity of the application (app) being spoken to. In pract…

Cited by 0Source ↗Scholar ↗
2018

RADMM: Recurrent Adaptive Mixture Model with Applications to Domain Robust Language Modeling

Kazuki Irie, Shankar Kumar, Michael Nirschl, Hank Liao
ICASSP 2018accepted

We present a new architecture and a training strategy for an adaptive mixture of experts with applications to domain robust language modeling. The proposed model is designed to benefit from the scenario where the training data are available in diverse domains as is the case for YouTube speech recogn…

Cited by 0Source ↗Scholar ↗