A deep learning method enhances MELP codec parameters directly in noisy environments for lower complexity than conventional signal-level enhancement while maintaining similar quality.
By directly enhancing the MELP parame- ters, the proposed algorithm was successfully combined with the MELP-based speech communication system
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Parameter Enhancement for MELP Speech Codec in Noisy Communication Environment
A deep learning method enhances MELP codec parameters directly in noisy environments for lower complexity than conventional signal-level enhancement while maintaining similar quality.