An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation
By Sibo Tong, Philip N. Garner, Hervé Bourlard. 2017
44 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Speech & Audio, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Shinji Watanabe
- Jinyu Li
- Takaaki Hori
- Matthew Wiesner
- Murali Karthick Baskar
- Florian Metze
- Dong Yu
- Nelson Yalta
In Speech & Audio
- Shinji Watanabe
- Takaaki Hori
- Jinyu Li
- Matthew Wiesner
- Murali Karthick Baskar
- Nelson Yalta
- Jaejin Cho
- Alan W. Black
In Signal Processing
- Shinji Watanabe
- Jinyu Li
- Takaaki Hori
- Matthew Wiesner
- Nelson Yalta
- Murali Karthick Baskar
- Florian Metze
- Jaejin Cho
Citations in the corpus
- Multilingual Speech Recognition with Corpus Relatedness Sampling (2019, background): “Other models have only one shared output layer to predict the universal phone set shared by all languages [10, 11, 12].”
- Sequence-Based Multi-Lingual Low Resource Speech Recognition (2018, background): “Other approaches [17, 18] constructed a shared language independent phone set, which could then also be adapted to the target language.”
- Multilingual Sequence-to-Sequence Speech Recognition: Architecture, Transfer Learning, and Language Modeling (2018, methodology): “In previous works [11, 30] related to hybrid DNN/RNN models and CTC based models [12, 15] the softmax layer is only adapted.”