Review of Time–Frequency Masking Approach for Improving Speech Intelligibility in Noise

Abstract

Over the last decade, time–frequency masking techniques have been explored to achieve substantial improvement of speech intelligibility in noise. Binary or soft mask can be applied to the noisy speech for speech separation. Binary masking approach retains the time–frequency (T–F) units of the noise-corrupted signal where the target speech is stronger than the interfering noise, and removes the T–F units where the interfering noise is dominant. While binary mask is 0 or 1, soft mask can take any value mostly in the range from 0 to 1, and is closely related to the frequency domain Wiener filter gain. Motivated by intelligibility studies of speech synthesized using the ideal binary (or soft) mask, a number of subsequent researches on estimating T–F mask have been conducted for practical use. This paper reviews the T–F masking strategies, covering the definition, preliminary studies with ideal mask, and the estimation of mask in practice.

KEYWORDS:

• Binary mask
• Classification
• Noise suppression
• Speech intelligibility
• Speech signal processing
• Time-frequency mask

Additional information

Notes on contributors

Gibak Kim

Gibak Kim received the BS and MS degrees in electronics engineering and the PhD degrees in electrical engineering from Seoul National University, Seoul, South Korea, in 1994, 1996, and 2007, respectively. From 1996 to 2000, he was with the Department of the Information Technology at LG Electronics Inc., Seoul, South Korea. He also worked at Voiceware Ltd. from 2000 to 2003, as a senior research engineer involved in the development of the automatic speech recognizer. From 2007 to 2010, he was a research associate at the University of Texas at Dallas, Richardson. He is currently with School of Electrical Engineering, Soongsil University, Seoul, South Korea. E-mail: [email protected]