An experimental study on joint modeling of mixed-bandwidth data via deep neural networks for robust speech recognition
By Jianqing Gao, Jun Du, Changqing Kong, Hua Lu, Enhong Chen, Chin-Hui Lee. 2016
9 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Model Architectures, Speech & Audio, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Khe Chai Sim
- Trevor Strohman
- Arun Narayanan
- Michiel Bacchiani
- Jinyu Li
- Tara N. Sainath
- Ananya Misra
- Bo Li
In Model Architectures
- Khe Chai Sim
- Michiel Bacchiani
- Arun Narayanan
- Parisa Haghani
- Golan Pundak
- Trevor Strohman
- Anshuman Tripathi
In Speech & Audio
- Khe Chai Sim
- Trevor Strohman
- Arun Narayanan
- Michiel Bacchiani
- Ananya Misra
- Mohamed G. Elfeky
- Parisa Haghani
- Golan Pundak
In Signal Processing
- Khe Chai Sim
- Trevor Strohman
- Arun Narayanan
- Michiel Bacchiani
- Jinyu Li
- Ananya Misra
- Bo Li
- Mohamed G. Elfeky
Citations in the corpus
- Toward Domain-Invariant Speech Recognition via Large Scale Training (2018, background): “z and 8 kHz. When computing features for 8 kHz input, the high frequency logmel bands are set to zeros. While more sophisticated techniques like reconstructing high frequency bands have been proposed [13], the gains over mixed bandwidth training are often small. Multiple application domains have typ”