Bilingual Streaming ASR with Grapheme units and Auxiliary Monolingual Loss
This work addresses bilingual speech recognition for specific locales like Spanish and Italian, offering incremental improvements in code-mixing capability.
The paper tackled bilingual automatic speech recognition for English as a secondary locale, introducing a solution with grapheme units and an auxiliary monolingual loss, resulting in improved word error rates, such as reducing WER from 46.5% to 13.8% for a code-mix Italian task.
We introduce a bilingual solution to support English as secondary locale for most primary locales in hybrid automatic speech recognition (ASR) settings. Our key developments constitute: (a) pronunciation lexicon with grapheme units instead of phone units, (b) a fully bilingual alignment model and subsequently bilingual streaming transformer model, (c) a parallel encoder structure with language identification (LID) loss, (d) parallel encoder with an auxiliary loss for monolingual projections. We conclude that in comparison to LID loss, our proposed auxiliary loss is superior in specializing the parallel encoders to respective monolingual locales, and that contributes to stronger bilingual learning. We evaluate our work on large-scale training and test tasks for bilingual Spanish (ES) and bilingual Italian (IT) applications. Our bilingual models demonstrate strong English code-mixing capability. In particular, the bilingual IT model improves the word error rate (WER) for a code-mix IT task from 46.5% to 13.8%, while also achieving a close parity (9.6%) with the monolingual IT model (9.5%) over IT tests.