PofoliaShared via Pofolia

IEEE/ACM Transactions on Audio Speech and Language Processing· 2014Q1

On Training Targets for Supervised Speech Separation

Yuxuan Wang, Arun Narayanan, DeLiang Wang

Short summary

Supervised speech separation models trained with ideal ratio mask (IRM) or FFT-MASK targets outperform those using ideal binary mask (IBM) or spectral envelope targets, showing improved objective intelligibility and quality metrics.

AI-generated from the title and abstract; the full text is not read.

TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app

The rest is in the Pofolia app

Takeaways, key points and questions to the paper; new summaries every day for your field. Free.

Sign in on the web to open

Field: Signal Processing

Signal ProcessingComputer Science