N-gram Boosting: Improving Contextual Biasing with Normalized N-gram Targets

no code implementations • 4 Aug 2023 • Wang Yau Li, Shreekantha Nadig, Karol Chang, Zafarullah Mahmood, Riqiang Wang, Simon Vandieken, Jonas Robertson, Fred Mailhot

Accurate transcription of proper names and technical terms is particularly important in speech-to-text applications for business conversations.

Encoder-decoder models for latent phonological representations of words

no code implementations • WS 2019 • Cass Jacobs, ra L., Fred Mailhot

We use sequence-to-sequence networks trained on sequential phonetic encoding tasks to construct compositional phonological representations of words.