Speaker and phoneme-aware speech bandwidth extension with residual dual-path network
Speech bandwidth extension aims to generate a wideband signal from a narrowband (low-band) input by predicting the missing high-frequency components. It is believed that the general knowledge about the speaker and phonetic content strengthens the prediction. In this paper, we propose to augment the...
Main Authors: | Hou, Nana, Xu, Chenglin, Pham, Van Tung, Zhou, Joey Tianyi, Chng, Eng Siong, Li, Haizhou |
---|---|
Other Authors: | School of Computer Science and Engineering |
Format: | Conference Paper |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/144854 |
Similar Items
-
Multi-task learning for end-to-end noise-robust bandwidth extension
by: Hou, Nana, et al.
Published: (2020) -
Domain adversarial training for speech enhancement
by: Hou, Nana, et al.
Published: (2020) -
Improving air traffic control speech intelligibility by reducing speaking rate effectively
by: Hou, Nana, et al.
Published: (2020) -
Pole-converging intrastage bandwidth extension technique for wideband amplifiers
by: Feng, Guangyin, et al.
Published: (2020) -
Speaker identification /
by: 333288 Nornini Shalydia Shaharin
Published: (2006)