3 accepted papers
Simulating the errors made by a speech recognizer on plain text has proven useful to help train downstream NLP tasks to be robust to real ASR errors at test time. Prior work in this domain has focused on modeling confusions at the phonetic level, and using a lexicon to convert from words to phones a…
Off-the-shelf speech recognition systems can yield useful results and accelerate application development, but general-purpose systems applied to specialized domains can introduce acoustically small-but semantically catastrophic-errors. Furthermore, sufficient audio data may not be available to devel…
For the task of speech enhancement, local learning objectives are agnostic to phonetic structures helpful for speech recognition. We propose to add a global criterion to ensure de-noised speech is useful for downstream tasks like ASR. We first train a spectral classifier on clean speech to predict s…