Mimicking Lombard Effect: An Analysis and Reconstruction

Ngo, Thuan Van; Kubo, Rieko; Akagi, Masato

doi:10.1587/transinf.2019edp7260

Cited by 3 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…sound pressure The sound pressure increases with the increase of noise [2] . energy increases with the increase of noise level [4] ;…”

Section: F1mentioning

confidence: 95%

“…Sebastian Rottschäfer [23] put forward an online lombard speech synthesis system, which also modifies the speech parameters according to the acoustic characteristics of lombard and the characteristics of noise environment. Thuan Van Ngo [4] designed a on-going rule generation model of speech features. Extract normal speech features and event positions, generate corresponding values of acoustic feature values under different conditions for speech with different noise levels through rule generation model.…”

Section: 2rule-based Transformation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Compensation of Lombard effect in speech enhancement

2023

Third International Conference on Digital Signal and Computer Communications (DSCC 2023)

View full text Add to dashboard Cite

Influenced by Lombard effect, the synthetic noisy speech training data commonly used in speech enhancement algorithm based on deep learning is different from the pronunciation under actual noise, which leads to the limited application performance of the algorithm in the actual environment. This paper summarizes the data compensation strategy proposed by researchers for speech enhancement algorithm under Lombard effect. However, these compensation strategies mainly focus on the front-end data processing part of speech enhancement, which improves the complexity of speech enhancement system.

show abstract

“…sound pressure The sound pressure increases with the increase of noise [2] . energy increases with the increase of noise level [4] ;…”

Section: F1mentioning

confidence: 95%

Section: 2rule-based Transformation Methodsmentioning

confidence: 99%