no code implementations • 3 Sep 2019 • Oluwatobi Olabiyi, Erik T. Mueller, Christopher Larson, Tarek Lahlou
Our experiments shows that adversarial bootstrapping is effective at addressing exposure bias, leading to improvement in response relevance and coherence.
no code implementations • 13 Jun 2019 • Chris Larson, Tarek Lahlou, Diana Mingels, Zachary Kulis, Erik Mueller
While techniques exist for desensitizing features to common noise patterns produced by Speech-to-Text (STT) and Text-to-Speech (TTS) systems, the question remains how to best leverage state-of-the-art language models (which capture rich semantic features, but are trained on only written text) on inputs with ASR errors.