Audio and Speech Processing Laboratory

Welcome to Audio and Speech Processing Lab (ASPL) of Iran University of Science and Technology. The audio and speech processing lab at Computer Engineering Department of iran university of science and technology is actively involved in research and imparting training at the graduate and under-graduate level through semester courses in the fields of speech processing. The lab was founded in 2002 and currently supports a group of researchers, graduate and under-graduate students engaged in solving the challenging problems in speech processing applications. In order to improve the industrial products, almost all the required data sets, softwares and hardwares are provided in the lab; so it is a suitable place for interested researchers to research in the following fields of speech processing.

  • Speech Signal Analysis
  • Discrete Speech Recognition
  • Speech Enhancement
  • Spoken Dialog Systems
  • Speech-based Human-Computer Interfaces
  • Voice over IP (VOIP)
  • Voice Applications on Web
  • Sound Source Localization
  • Keyword Spotting
  • Language Modelling
  • Speaker Adaptation


Related Centers and Groups


Latest News

PhD candidate Behzad Zamani defended his thesis on Tuesday June 19th, succefully.

 The 20th Iranian Conference on Electrical Engineering (ICEE) is organized by the University of Tehran in co-operation with the permanent Secretariat of the Iranian Electrical Engineering Conference. The conference will be held in Tehran from 15-17 May, 2012. We have 2 oral presentations: 1) "Two-Microphone Speech Enhancement Using a Learned Binary Mask" by Rouhollah Abdipour 2) "A Classifier Combination Approach for Farsi Accents Recognition"  by Shahab Jalalvand