Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Gyeongmin Kim

Gyeongmin Kim

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Audio and Speech Processing×2Sound×2

Research Timeline

2026
Extracting Voice Styles from Frozen TTS Models via Gradient-Based Inverse Optimization

The paper describes a method to optimize the style vector for text-to-speech systems without a reference encoder, improving similarity and acceptance rate.

faster-enhancer.c: A Dependency-Free int8 Runtime for Streaming Speech Enhancement on Commodity CPUs

This paper implements and measures the cost of running a streaming speech enhancer on a CPU, achieving a 3.3x speedup compared to the fp32 ONNX Runtime graph.

Highlighted terms show continued research focus across papers

Papers

eess.AScs.SDNEWEmpiricalJul 28, 2026

Extracting Voice Styles from Frozen TTS Models via Gradient-Based Inverse Optimization

Gyeongmin Kim

The paper describes a method to optimize the style vector for text-to-speech systems without a reference encoder, improving similarity and acceptance rate.

View →
eess.AScs.SD
NEW
Empirical
Jul 28, 2026

faster-enhancer.c: A Dependency-Free int8 Runtime for Streaming Speech Enhancement on Commodity CPUs

Gyeongmin Kim

This paper implements and measures the cost of running a streaming speech enhancer on a CPU, achieving a 3.3x speedup compared to the fp32 ONNX Runtime graph.

View →