Deferred NAM: Low-latency Top-K Context Injection via Deferred Context Encoding for Non-Streaming ASR.
Zelin WuGan SongChristopher LiPat RondonZhong MengXavier VelezWeiran WangDiamantino CaseiroGolan PundakTsendsuren MunkhdalaiAngad ChandorkarRohit PrabhavalkarPublished in: CoRR (2024)