A Multiscale Autoencoder (MSAE) Framework for End-to-End Neural Network Speech Enhancement

Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a multiscale autoencoder (MSAE) for mask-based end-to-end neur...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE/ACM transactions on audio, speech, and language processing Ročník 32; s. 2418 - 2431
Hlavní autoři: Borgstrom, Bengt J., Brandstein, Michael S.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Piscataway IEEE 2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Automatic speech recognition
Decoding
Ear
end-to-end neural networks
multiscale representations
mutliresolution transforms
Network topologies
Neural networks
Parameterization
Signal resolution
Speech
Speech enhancement
Speech processing
Speech recognition
Time-frequency analysis
Transforms
Voice recognition
Waveforms
ISSN:2329-9290, 2329-9304
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Neural network approaches to single-channel speech enhancement have received much recent attention. In particular, mask-based architectures have achieved significant performance improvements over conventional methods. This paper proposes a multiscale autoencoder (MSAE) for mask-based end-to-end neural network speech enhancement. The MSAE performs spectral decomposition of an input waveform within separate band-limited branches, each operating with a different rate and scale, to extract a sequence of multiscale embeddings. The proposed framework features intuitive parameterization of the autoencoder, including a flexible spectral band design based on the Constant-Q transform. Additionally, the MSAE is constructed entirely of differentiable operators, allowing it to be implemented within an end-to-end neural network, and be discriminatively trained. The MSAE draws motivation both from recent multiscale network topologies and from traditional multiresolution transforms in speech processing. Experimental results show the MSAE to provide clear performance benefits relative to conventional single-branch autoencoders. Additionally, the proposed framework is shown to outperform a variety of state-of-the-art enhancement systems, both in terms of objective speech quality metrics and automatic speech recognition accuracy.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2329-9290
2329-9304
DOI:10.1109/TASLP.2024.3389632