EUVIMEDEUVIMED entdecken
Crossref

EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment

Daipeng Zhang, Wenhuan Lu, Xianghu Yue, Hongcheng Zhang, Jianguo Wei

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (41) · 34656-34664

DOI: 10.1609/aaai.v40i41.40766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Daipeng Zhang und 4 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Dysarthric speech reconstruction (DSR) aims to enhance the intelligibility of dysarthric speech. Compared with normal speech, the dysarthric speech is characterized by its pathological features, including discontinuous pronunciation, slow speech, hoarseness, and improper pauses. Significant disparities in the feature space between normal and dysarthric speech may result in suboptimal speech reconstruction, thereby degrading speech intelligibility. To enhance the reconstruction ability of speech feature spaces, this paper proposes a DSR model named the Encoding-Aligned Variational Autoencoder (EA-VAE). By incorporating alignment modules of frame-level embedding features, prior distributions, and duration into the encoder of the VAE, the model explicitly aligns the dysarthric speech encoding with a representation of the parallel normal speech. A shared decoder is then used to generate speech with improved intelligibility. Experimental results on the UASpeech benchmark confirm that EA-VAE achieves state-of-the-art performance, with a 31.7% relative word error rate reduction and the highest subjective MOS score (4.48), thoroughly validating the effectiveness and advancements of the proposed method in dysarthric speech reconstruction.

Zitieren

APA

Zhang, D., Lu, W., Yue, X., Zhang, H., & Wei, J. (2026). EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 40(41), 34656-34664. https://doi.org/10.1609/aaai.v40i41.40766

Vancouver

Zhang D, Lu W, Yue X, Zhang H, Wei J. EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(41):34656-34664. doi:10.1609/aaai.v40i41.40766

BibTeX
@article{Zhang2026,
  author = {Zhang, Daipeng and Lu, Wenhuan and Yue, Xianghu and Zhang, Hongcheng and Wei, Jianguo},
  title = {EA-VAE: Learning to Reconstruct Dysarthric Speech via Variational Autoencoder with Encoding Alignment},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {41},
  pages = {34656--34664},
  doi = {10.1609/aaai.v40i41.40766}
}
Kostenlos starten →