A data-independent, sector-based beamformer used as a training-free front-end improves word error rate by up to 11% relative on the AMI meeting corpus for a multichannel MFCCA-based multi-speaker ASR system.
M2Met: The ICASSP 2022 Multi-Channel Multi-Party Meeting Transcription Challenge,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Data-independent Beamforming for End-to-end Multichannel Multi-speaker ASR
A data-independent, sector-based beamformer used as a training-free front-end improves word error rate by up to 11% relative on the AMI meeting corpus for a multichannel MFCCA-based multi-speaker ASR system.