End-to-End Model for Speech Enhancement by Consistent Spectrogram Masking
This addresses a specific issue in speech enhancement for audio processing applications, but it is incremental as it builds on existing complex-valued spectrogram methods.
The paper tackled the problem of inconsistent spectrogram masking in speech enhancement, which causes unintended artifacts, by proposing Consistency Spectrogram Masking (CSM) to enforce constraints, resulting in accelerated training and significant improvements in speech quality.
Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT) spectrogram based training targets, e.g. Complex RatioMask (cRM) [1]. However, masking on spectrogram would violentits consistency constraints. In this work, we prove that theinconsistent problem enlarges the solution space of the speechenhancement model and causes unintended artifacts. ConsistencySpectrogram Masking (CSM) is proposed to estimate the complexspectrogram of a signal with the consistency constraint in asimple but not trivial way. The experiments comparing ourCSM based end-to-end model with other methods are conductedto confirm that the CSM accelerate the model training andhave significant improvements in speech quality. From ourexperimental results, we assured that our method could enha