← Search

Mi Suk Lee

2 accepted papers

2020

A Dual-Staged Context Aggregation Method towards Efficient End-to-End Speech Enhancement

ICASSP 2020accepted

In speech enhancement, an end-to-end deep neural network converts a noisy speech signal to a clean speech directly in the time domain without time-frequency transformation or mask estimation. However, aggregating contextual information from a high-resolution time domain signal with an affordable mod…

Cited by 0SourceScholar
2020

Efficient and Scalable Neural Residual Waveform Coding with Collaborative Quantization

ICASSP 2020accepted

Scalability and efficiency are desired in neural speech codecs, which supports a wide range of bitrates for applications on various devices. We propose a collaborative quantization (CQ) scheme to jointly learn the codebook of LPC coefficients and the corresponding residuals. CQ does not simply shoeh…

Cited by 0SourceScholar