A new benchmark, ERSB, shows that neural speech codecs in noisy environments degrade both reconstruction quality and downstream speech enhancement and recognition consistency.
92370206), the Shanghai Municipal Science and Technol- ogy Major Project (2021SHZDZX0102) and the Key Re- search and Development Program of Jiangsu Province, China (No.BE2022059)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SD 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency
A new benchmark, ERSB, shows that neural speech codecs in noisy environments degrade both reconstruction quality and downstream speech enhancement and recognition consistency.