Text Injection for Neural Contextual Biasing
Neural contextual biasing effectively improves automatic speech recognition (ASR) for
crucial phrases within a speaker's context, particularly those that are infrequent in the …
crucial phrases within a speaker's context, particularly those that are infrequent in the …
Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition
J Chen, J Fang, Y Zheng, Y Wang, H Fei - arXiv preprint arXiv:2407.03026, 2024 - arxiv.org
Currently, end-to-end (E2E) speech recognition methods have achieved promising
performance. However, auto speech recognition (ASR) models still face challenges in …
performance. However, auto speech recognition (ASR) models still face challenges in …
Implementation of an Automatic Meeting Minute Generation System Using YAMNet with Speaker Identification and Keyword Prompts
CT Lu, LY Wang - Applied Sciences, 2024 - mdpi.com
Featured Application The proposed system can automatically generate conference/meeting
minutes with labeled speakers and produce keyword spotting. So, the proposed system …
minutes with labeled speakers and produce keyword spotting. So, the proposed system …
Bridging Gaps in Russian Language Processing: AI and Everyday Conversations
T Sherstinova, N Mikhaylovskiy… - … 35th Conference of …, 2024 - ieeexplore.ieee.org
Contemporary advancements in NLP and neural network techniques are paving the way to
enhance and harness traditional linguistic resources and corpora, as well as expand the …
enhance and harness traditional linguistic resources and corpora, as well as expand the …