Paper ID | SPE-6.2 | ||
Paper Title | TRAINING NOISY SINGLE-CHANNEL SPEECH SEPARATION WITH NOISY ORACLE SOURCES: A LARGE GAP AND A SMALL STEP | ||
Authors | Matthew Maciejewski, Johns Hopkins University, United States; Jing Shi, Chinese Academy of Sciences, United States; Shinji Watanabe, Sanjeev Khudanpur, Johns Hopkins University, United States | ||
Session | SPE-6: Speech Enhancement 2: Speech Separation and Dereverberation | ||
Location | Gather.Town | ||
Session Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation Time: | Tuesday, 08 June, 14:00 - 14:45 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-ENHA] Speech Enhancement and Separation | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | As the performance of single-channel speech separation systems has improved, there has been a desire to move to more challenging conditions than the clean, near-field speech that initial systems were developed on. When training deep learning separation models, a need for ground truth leads to training on synthetic mixtures. As such, training in noisy conditions requires either using noise synthetically added to clean speech, preventing the use of in-domain data for a noisy-condition task, or training using mixtures of noisy speech, requiring the network to additionally separate the noise. We demonstrate the relative inseparability of noise and that this noisy speech paradigm leads to significant degradation of system performance. We also propose an SI-SDR–inspired training objective that tries to exploit the inseparability of noise to implicitly partition the signal and discount noise separation errors, enabling the training of better separation systems with noisy oracle sources. |