WaveNet conditioned on log-mel spectrograms upsamples 8 kHz GSM-FR speech to 24 kHz and reaches perceptual quality close to 16 kHz AMR-WB in MUSHRA listening tests.
Waveform modeling using stacked di- lated convolutional neural networks for speech bandwidth ex- tension
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Speech bandwidth extension with WaveNet
WaveNet conditioned on log-mel spectrograms upsamples 8 kHz GSM-FR speech to 24 kHz and reaches perceptual quality close to 16 kHz AMR-WB in MUSHRA listening tests.