We propose a neural language modeling system based on low-rank adaptation (LoRA) for
speech recognition output rescoring. Although pretrained language models (LMs) like BERT …

Existing research suggests that automatic speech recognition (ASR) models can benefit
from additional contexts (eg, contact lists, user specified vocabulary). Rare words and …

Contextualized end-to-end automatic speech recognition has been an active research area,
with recent efforts focusing on the implicit learning of contextual phrases based on the final …

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 …

In speech recognition applications, it is important to recognize context-specific rare words,
such as proper nouns. Tree-constrained Pointer Generator (TCPGen) has shown promise …

End-to-end (E2E) automatic speech recognition (ASR) models have become standard
practice for various commercial applications. However, in real-world scenarios, the long …

Automatic Speech Recognition (ASR) still face challenges when recognizing time-variant
rare-phrases. Contextual biasing (CB) modules bias ASR model towards such contextually …

This paper proposes Transducers with Pronunciation-aware Embeddings (PET). Unlike
conventional Transducers where the decoder embeddings for different tokens are trained …

Context cues carry information which can improve multi-turn interactions in automatic
speech recognition (ASR) systems. In this paper, we introduce a novel mechanism inspired …

Years of scholarly efforts have led to extensive studies on end-to-end automatic speech
recognition (E2E ASR), now demonstrating robust performance in everyday applications …