Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as
quickly and accurately as possible. However, emitting fast without degrading quality, as …

Streaming automatic speech recognition (ASR) aims to emit each hypothesized word as
quickly and accurately as possible, while full-context ASR waits for the completion of a full …

Interactive speech recognition systems must generate words quickly while also producing
accurate results. Two-pass models excel at these requirements by employing a first-pass …

Transformer 作为一种新的深度学习算法框架, 得到了越来越多研究人员的关注,
成为目前的研究热点. Transformer 模型中的自注意力机制受人类只关注于重要事物的启发 …

We study the problem of word-level confidence estimation in subword-based end-to-end
(E2E) models for automatic speech recognition (ASR). Although prior works have proposed …

Language is by its very nature incremental in how it is produced and processed. This
property can be exploited by NLP systems to produce fast responses, which has been …

In automatic speech recognition (ASR) rescoring, the hypothesis with the fewest errors
should be selected from the n-best list using a language model (LM). However, LMs are …

This work introduces cross-attention conformer, an attention-based architecture for context
modeling in speech enhancement. Given that the context information can often be …

End-to-end (E2E) spoken language understanding (SLU) systems that generate a semantic
parse from speech have become more promising recently. This approach uses a single …

Multilingual end-to-end automatic speech recognition models are attractive due to its
simplicity in training and deployment. Recent work on large-scale training of such models …