2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDSPE-50.5
Paper Title RECURRENT PHASE RECONSTRUCTION USING ESTIMATED PHASE DERIVATIVES FROM DEEP NEURAL NETWORKS
Authors Lars Thieling, Daniel Wilhelm, Peter Jax, Institute of Communication Systems, RWTH Aachen University, Germany
SessionSPE-50: Voice Conversion & Speech Synthesis: Singing Voice & Other Topics
LocationGather.Town
Session Time:Friday, 11 June, 11:30 - 12:15
Presentation Time:Friday, 11 June, 11:30 - 12:15
Presentation Poster
Topic Speech Processing: [SPE-SYNT] Speech Synthesis and Generation
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
Abstract This paper presents a deep neural network (DNN)-based system for phase reconstruction of speech signals solely from their magnitude spectrograms. The phase is very sensitive to time shifts. Therefore it is meaningful to estimate the phase derivatives instead of the phase directly, e.g., using DNNs and then apply a phase reconstruction method to recombine these estimates to a suitable phase spectrum. In this paper, we propose three changes for such a two-stage phase reconstruction system. For estimating phase derivatives using DNNs, we propose 1) a new regularized cosine loss function and 2) a preprocessing step for the phase derivatives that eliminates systematic offsets in the data. The experimental results demonstrate that these two changes reduce the training duration and stabilize the training with respect to hyperparameter variations. Furthermore, we propose 3) a new simple but effective averaging of weighted derivative estimates for the subsequent phase reconstruction method. Experimental results confirm that the proposed reconstruction method surpasses state-of-the-art systems both in terms of the reconstructed phase spectra and the overall achieved speech quality.