Note: This bibliographic page is archived and will no longer be updated. For an up-to-date list of publications from the Music Technology Group see the Publications list .

Development of a Sound Coding Strategy based on a Deep Recurrent Neural Network for Monaural Source Separation in Cochlear Implants

Title Development of a Sound Coding Strategy based on a Deep Recurrent Neural Network for Monaural Source Separation in Cochlear Implants
Publication Type Conference Paper
Year of Publication 2016
Conference Name 12th ITG conference on Speech Communication
Authors Nogueira, W. , Gajęcki T. , Krüger B. , Janer J. , & Büchner A.
Conference Start Date 05/10/2016
Publisher IEEE
Conference Location Paderborn, Germany
Abstract The aim of this study is to investigate whether a source separation algorithm based on a deep recurrent neural network (DRNN) can provide a speech perception benefit for cochlear implant users when speech signals are mixed with another competing voice. The DRNN is based on an existing architecture that is used in combination with an extra masking layer for optimization. The approach has been evaluated using the HSM sentence test (male voice) mixed with a competing voice (female voice) for a monaural speech separation task. Two DRNNs with two levels of complexity have been used. The algorithms have been evaluated in 8 normal hearing listeners using a Vocoder and in 3 CI users. Both DRNNs show a large and significant improvement in speech intelligibility using Vocoded speech. Preliminary results in 3 CI users seem to confirm the improvement observed using Vocoded simulations.
preprint/postprint document http://hdl.handle.net/10230/33115