Cargando…
Domain Adaptation with Augmented Data by Deep Neural Network Based Method Using Re-Recorded Speech for Automatic Speech Recognition in Real Environment
The most effective automatic speech recognition (ASR) approaches are based on artificial neural networks (ANN). ANNs need to be trained with an adequate amount of matched conditioned data. Therefore, performing training adaptation of an ASR model using augmented data of matched condition as the real...
Autores principales: | Nahar, Raufun, Miwa, Shogo, Kai, Atsuhiko |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9782479/ https://www.ncbi.nlm.nih.gov/pubmed/36560315 http://dx.doi.org/10.3390/s22249945 |
Ejemplares similares
-
Domain Generalization for Language-Independent Automatic Speech Recognition
por: Gao, Heting, et al.
Publicado: (2022) -
Multi-resolution speech analysis for automatic speech recognition using deep neural networks: Experiments on TIMIT
por: Toledano, Doroteo T., et al.
Publicado: (2018) -
Automatic Speech Recognition from Neural Signals: A Focused Review
por: Herff, Christian, et al.
Publicado: (2016) -
Deep Spiking Neural Networks for Large Vocabulary Automatic Speech Recognition
por: Wu, Jibin, et al.
Publicado: (2020) -
Brain-inspired speech segmentation for automatic speech recognition using the speech envelope as a temporal reference
por: Lee, Byeongwook, et al.
Publicado: (2016)