Deferred NAM: Low-latency Top-K Context Injection via DeferredContext Encoding for Non-Streaming ASR

arXiv:2404.10180v1 Announce Type: cross
Abstract: Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data. Attention-based biasing is a leading approach which allows for full end-to-end cotraining of the recognizer and biasing system and requires no separate inference-time components. Such biasers typically consist of a context encoder; followed by a context filter which narrows down the context to apply, improving per-step …

abstract arxiv asr attention context cs.ai cs.cl cs.lg cs.ne data eess.as encoding latency low speaker speech streaming training training data transcribe type via