Off-the-shelf speech recognizers are error-prone in specialized domains; we aim to mitigate the impact of these errors for downstream classification tasks without in-domain speech training data, by augmenting available typewritten text training data with inferred phonetic information. We apply our method to mitigate the effects of the lack of speech training data when converting a typed chatbot to a spoken language interface.

Paper available here: https://ieeexplore.ieee.org/document/8682550