Journal
Publisher
ISCA-INT SPEECH COMMUNICATION ASSOC
DOI: 10.21437/Interspeech.2018-1888
Keywords
speech recognition; capsule network; routing-by-agreement; convolutional neural network
Categories
Funding
- Engineering Research Center of Excellence (ERC) Program
- National Research Foundation (NRF), Korean Ministry of Science ICT (MSIT) [NRF-2017R1A5A1014708]
- ICT R&D program of MSIP/IITP [R-20161130-004520]
- KIST Institutional Program [2E27810-18-P034]
- ETUDE CORPORATION [G01180051]
- Brain Korea 21+ Project, BK Electronics and Communications Technology Division, KAIST
- KOLON Corporation, Korea through the KOLON-KAIST Lifestyle Innovation Center Project [LSI17-ITKDS0001]
Ask authors/readers for more resources
In recent years, neural networks have become one of the common approaches used in speech recognition(SR), with SR systems based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) achieving the state-of-the-art results in various SR benchmarks. Especially, since CNNs are capable of capturing the local features effectively, they are applied to tasks which have relatively short-term dependencies, such as keyword spotting or phoneme-level sequence recognition. However, one limitation of CNNs is that, with max pooling, they do not consider the pose relationship between low-level features. Motivated by this problem, we apply the capsule network to capture the spatial relationship and pose information of speech spectrogram features in both frequency and time axes. We show that our proposed end-to-end SR system with capsule networks on one-second speech commands dataset achieves better results on both clean and noise-added test than baseline CNN models.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available