Data Augmentation Based on Vowel Stretch for Improving Children's Speech Recognition
- Tohru Nagano
- Takashi Fukuda
- et al.
- 2019
- ASRU 2019
Conference paper
Publications
35 results for Takashi Fukuda
Mixed Bandwidth Acoustic Modeling Leveraging Knowledge Distillation
- 2019
- ASRU 2019
Conference paperDirect neuron-wise fusion of cognate neural networks
- Takashi Fukuda
- Masayuki Suzuki
- et al.
- 2019
- INTERSPEECH 2019
Conference paperAutomated testing of basic recognition capability for speech recognition systems
- Futoshi Iwama
- Takashi Fukuda
- 2019
- ICST 2019
Conference paperData augmentation improves recognition of foreign accented speech
- Takashi Fukuda
- Raul Fernandez
- et al.
- 2018
- INTERSPEECH 2018
Conference paperDetecting breathing sounds in realistic Japanese telephone conversations and its application to automatic speech recognition
- Takashi Fukuda
- Osamu Ichikawa
- et al.
- 2018
- Speech Communication
PaperEnsembles of multi-scale VGG acoustic models
- Michael Heck
- Masayuki Suzuki
- et al.
- 2017
- INTERSPEECH 2017
Conference paperEfficient knowledge distillation from an ensemble of teachers
- Takashi Fukuda
- Masayuki Suzuki
- et al.
- 2017
- INTERSPEECH 2017
Conference paperHarmonic feature fusion for robust neural network-based acoustic modeling
- Osamu Ichikawa
- Takashi Fukuda
- et al.
- 2017
- ICASSP 2017
Conference paperEffective joint training of denoising feature space transforms and Neural Network based acoustic models
- Takashi Fukuda
- Osamu Ichikawa
- et al.
- 2017
- ICASSP 2017
Conference paper