Subjective quality evaluation of personalized own voice reconstruction systems

Open Access

Figure 2.

DNN-based own voice reconstruction system based on the FT-JNF architecture from [24]. The first LSTM layer operates in frequency direction (F-LSTM) and the second LSTM layer operates in time direction (T-LSTM). Figure adapted from [18].

Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.

Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.

Initial download of the metrics may take a while.