most citedTelephonetic: Making Neural Language Models Robust to ASR and Semantic Noise

1 citations · 1 across the 1 of their papers we have counts for

collaborators

2 papers

cs.CL2019

Adversarial Bootstrapping for Dialogue Model Training

Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson +1

Open domain neural dialogue models, despite their successes, are known to produce responses that lack relevance, diversity, and in many cases coherence. These shortcomings stem fro…

eess.AS2019★ 1 cited

Telephonetic: Making Neural Language Models Robust to ASR and Semantic Noise

Chris Larson, Tarek Lahlou, Diana Mingels +2

Speech processing systems rely on robust feature extraction to handle phonetic and semantic variations found in natural language. While techniques exist for desensitizing features…