This paper introduces FunASR, an open-source speech recognition toolkit designed to
bridge the gap between academic research and industrial applications. FunASR offers …

The demand for ophthalmic diagnosis and monitoring equipment is high due to day-by-day
increasing eye-related diseases. These diseases are growing very fast due to changes in …

Attention-based contextual biasing approaches have shown significant improvements in the
recognition of generic and/or personal rare-words in End-to-End Automatic Speech …

Streaming speech recognition architectures are employed for low-latency, real-time
applications. Such architectures are often characterized by their causality. Causal …

The local and global features are both essential for automatic speech recognition (ASR).
Many recent methods have verified that simply combining local and global features can …

Conformer is an extension of transformer-based neural ASR models whose fundamental
component is the selfattention module. In this paper, we show that we can remove the self …

Recently, self-attention-based transformers and conformers have been introduced as
alternatives to RNNs for ASR acoustic modeling. Nevertheless, the full-sequence attention …

For most automatic speech recognition systems, many unacceptable hypothesis errors still
make the recognition results absurd and difficult to understand. In this paper, we introduce …

We introduce TitaNet-LID, a compact end-to-end neural network for Spoken Language
Identification (LID) that is based on the ContextNet architecture. TitaNet-LID employs 1D …

We present dual-attention neural biasing, an architecture designed to boost Wake Words
(WW) recognition and improve inference time latency on speech recognition tasks. This …