Frontier Research on Low-Resource Speech Recognition Technology
W Slam, Y Li, N Urouvas - Sensors, 2023 - mdpi.com
With the development of continuous speech recognition technology, users have put forward
higher requirements in terms of speech recognition accuracy. Low-resource speech …
higher requirements in terms of speech recognition accuracy. Low-resource speech …
Wake word detection with alignment-free lattice-free MMI
Always-on spoken language interfaces, eg personal digital assistants, rely on a wake word
to start processing spoken input. We present novel methods to train a hybrid DNN/HMM …
to start processing spoken input. We present novel methods to train a hybrid DNN/HMM …
Channel-wise av-fusion attention for multi-channel audio-visual speech recognition
G Xu, S Yang, W Li, S Wang, G Wei… - ICASSP 2022-2022 …, 2022 - ieeexplore.ieee.org
In this paper, we present our work for automatic speech recognition (ASR) in the Multimodal
Information Based Speech Processing (MISP) Challenge 2021. We proposed a combination …
Information Based Speech Processing (MISP) Challenge 2021. We proposed a combination …
The JHU multi-microphone multi-speaker ASR system for the CHiME-6 challenge
This paper summarizes the JHU team's efforts in tracks 1 and 2 of the CHiME-6 challenge for
distant multi-microphone conversational speech diarization and recognition in everyday …
distant multi-microphone conversational speech diarization and recognition in everyday …
[PDF][PDF] The TNT Team System Descriptions of Cantonese and Mongolian for IARPA OpenASR20.
This paper presents our work for OpenASR20 Challenge. We describe our Automatic
Speech Recognition (ASR) systems for Cantonese and Mongolian under both constrained …
Speech Recognition (ASR) systems for Cantonese and Mongolian under both constrained …
Wake word detection and its applications
Y Wang - 2021 - jscholarship.library.jhu.edu
Always-on spoken language interfaces, eg personal digital assistants, rely on a wake word
to start processing spoken input. Novel methods are proposed to train a wake word …
to start processing spoken input. Novel methods are proposed to train a wake word …
Space-and-speaker-aware acoustic modeling with effective data augmentation for recognition of multi-array conversational speech
We propose a space-and-speaker-aware (SSA) approach to acoustic modeling (AM),
denoted as SSA-AM, to improve system performances of automatic speech recognition …
denoted as SSA-AM, to improve system performances of automatic speech recognition …
Collaborative training of acoustic encoder for recognizing the impaired children speech
SR Shareef, YF Mohammed - 2022 Fifth College of Science …, 2022 - ieeexplore.ieee.org
Encoder-decoder models have become an effective approach and are increasingly popular
for sequence learning tasks like automatic speech recognition (ASR) due to their simplified …
for sequence learning tasks like automatic speech recognition (ASR) due to their simplified …
VACE-WPE: Virtual acoustic channel expansion based on neural networks for weighted prediction error-based speech dereverberation
JY Yang, JH Chang - IEEE/ACM Transactions on Audio …, 2021 - ieeexplore.ieee.org
Speech dereverberation is an important issue for many real-world speech processing
applications. Among the techniques developed, the weighted prediction error (WPE) …
applications. Among the techniques developed, the weighted prediction error (WPE) …
[PDF][PDF] Child Speech Recognition as Low Resource Automatic Speech Recognition
F Wu - 2020 - jscholarship.library.jhu.edu
This thesis investigates child speech recognition as a low-resource scenario of automatic
speech recognition (ASR), and explores multiple methods to improve the performance of …
speech recognition (ASR), and explores multiple methods to improve the performance of …