4 papers
Cross-Speaker Encoding Network for Multi-Talker Speech Recognition
Jiawen Kang, Lingwei Meng, Mingyu Cui +4
End-to-end multi-talker speech recognition has garnered great interest as an effective approach to directly transcribe overlapped speech from multiple speakers. Current methods typ…
Investigation of Deep Neural Network Acoustic Modelling Approaches for Low Resource Accented Mandarin Speech Recognition
Xurong Xie, Xiang Sui, Xunying Liu +1
The Mandarin Chinese language is known to be strongly influenced by a rich set of regional accents, while Mandarin speech with each accent is quite low resource. Hence, an importan…
Variational Auto-Encoder Based Variability Encoding for Dysarthric Speech Recognition
Xurong Xie, Rukiye Ruzi, Xunying Liu +1
Dysarthric speech recognition is a challenging task due to acoustic variability and limited amount of available data. Diverse conditions of dysarthric speakers account for the acou…
Bayesian Learning for Deep Neural Network Adaptation
Xurong Xie, Xunying Liu, Tan Lee +1
A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Speaker adaptation techn…