WHAM! extends speech separation evaluation to realistic noisy conditions via a new public dataset of WSJ0-2mix mixtures plus ambient noise, with benchmarks showing reduced yet positive separation gains.
Phasebook and friends: Leveraging discrete representa- tions for source separation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
WHAM!: Extending Speech Separation to Noisy Environments
WHAM! extends speech separation evaluation to realistic noisy conditions via a new public dataset of WSJ0-2mix mixtures plus ambient noise, with benchmarks showing reduced yet positive separation gains.