Speech intelligibility improvement in noisy environments based on energy correlation in frequency bands

详细信息    查看全文

• 作者：Peyman Goli ^{p.goli@stu.nit.ac.ir}Author Vitae ; Mohammad Reza Karami-mollaei ; ^{mkarami@nit.ac.ir}Author Vitae
• 关键词：Speech intelligibility ; Speech modification ; Energy correlation ; Function optimization
• 刊名：Digital Signal Processing
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：62
• 期：Complete
• 页码：238-248
• 全文大小：2664 K
• 卷排序：62

文摘

Speech intelligibility is improved in background noise without increasing speech energy. The fundamental idea is based on maximizing an intelligibility measure (STOI). Spectral energy correlation of clean and noisy speeches is optimized within each frame.