Digital Speech Transmission: Enhancement, Coding and Error Concealment

389 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

On the information rate of speech communication (2017, methodology): “where we modeled the phase of the STFT of a speech signal as a uniformly distributed random variable between−π and π that is statistically independent to the magnitude [14].”
Convolutional Neural Networks to Enhance Coded Speech (2018, methodology): “approaches are conducted as a transmitter-sided preprocessing step to suppress the background noise before the speech signal is coded and transmitted [19].”
Deep learning for minimum mean-square error approaches to speech enhancement (2019, positive): “Noisy speech s analysed frame-wise using the running STFT ( Vary and Martin, 2006 ): c ( 𝑛, 𝑘 ) = 𝑁 𝑙 −1 ∑ 𝑚 =0 𝑥 ( 𝑚 + 𝑛𝑁 𝑠 ) 𝑤 ( 𝑚 ) 𝑒 − 𝑗2 𝜋𝑚𝑘 ∕ 𝑁 𝑙 , (2) here n denotes the frame index, k denotes the discrete-frequency index, l denotes the frame length in discrete-time…”