1
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      Phase-aware deep speech enhancement: It's all about the frame length.

      1 , 1
      JASA express letters
      Acoustical Society of America (ASA)

      Read this article at

      ScienceOpenPublisherPubMed
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          Algorithmic latency in speech processing is dominated by the frame length used for Fourier analysis, which in turn limits the achievable performance of magnitude-centric approaches. As previous studies suggest the importance of phase grows with decreasing frame length, this work presents a systematic study on the contribution of phase and magnitude in modern deep neural network (DNN)-based speech enhancement at different frame lengths. Results indicate that DNNs can successfully estimate phase when using short frames, with similar or better overall performance compared to using longer frames. Thus, interestingly, modern phase-aware DNNs allow for low-latency speech enhancement at high quality.

          Related collections

          Author and article information

          Journal
          JASA Express Lett
          JASA express letters
          Acoustical Society of America (ASA)
          2691-1191
          2691-1191
          Oct 2022
          : 2
          : 10
          Affiliations
          [1 ] Signal Processing (SP), Universität Hamburg, Germany tal.peer@uni-hamburg.de, timo.gerkmann@uni-hamburg.de.
          Article
          10.1121/10.0014875
          36319213
          26f98f60-af07-4519-ab73-045548bd6b12
          History

          Comments

          Comment on this article