Multi-Modal automatic speech recognition (ASR) techniques aim to leverag...
Hotword customization is one of the important issues remained in ASR fie...
This paper introduces FunASR, an open-source speech recognition toolkit
...
Estimating confidence scores for recognition results is a classic task i...
Conventional ASR systems use frame-level phoneme posterior to conduct
fo...
Semantic understanding of 3D point cloud relies on learning models with
...
General accent recognition (AR) models tend to directly extract low-leve...
Neural architecture search (NAS) has been successfully applied to tasks ...
The variety of accents has posed a big challenge to speech recognition. ...
Semantic segmentation of 3D point clouds relies on training deep models ...
End-to-end models are favored in automatic speech recognition (ASR) beca...
Point set is arguably the most direct approximation of an object or scen...
Code-switching (CS) is a common phenomenon and recognizing CS speech is
...
The stabilizer group for an n-qubit state |ϕ〉 is the set of all
invertib...