Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling

By Lahiru Samarakoon, Khe Chai Sim. 2016

73 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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

1. Jinyu Li
2. Dong Yu
3. Tara N. Sainath
4. Yifan Gong
5. Bo Li
6. Li Deng
7. Khe Chai Sim
8. Arun Narayanan

In Signal Processing

1. Jinyu Li
2. Dong Yu
3. Yifan Gong
4. Tara N. Sainath
5. Khe Chai Sim
6. Bo Li
7. Li Deng
8. Arun Narayanan

Citations in the corpus

• Personalization of End-to-End Speech Recognition on Mobile Devices for Named Entities (2019, background): “There are existing speaker adaptation techniques for neural networks that offer a more compact model representation by having a large number of global parameters shared across different speakers and a smaller number of speaker-specific parameters [13, 14, 15, 16, 17, 18, 19, 20].”
• Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition (2018, methodology): “In this paper, we investigate the use of Factorized Hidden Layer (FHL) [9] to impose a low-rank constraint to reduce the number of domain-specific parameters.”
• Recent progresses in deep learning based acoustic models (2017, methodology): “A solution is to use FHL [115], [116] which constrains the bases to be rank-1 matrices.”
• An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models (2019, unknown): “A common solution to this problem is to adapt a well-trained model using a small amount of user-specific data to build a personalized model for each user [4, 5, 6, 7, 8, 9, 10, 11, 12, 13].”
• Embedding-Based Speaker Adaptive Training of Deep Neural Networks (2017, background): “In [18], factorized hidden layers (FHL) are constructed as a linear combination of speaker dependent bases for neural network adaptation.”
• Speaker-Invariant Training Via Adversarial Learning (2018, background): “Therefore, speaker adaptation meth-ods are widely used to boost the recognition system performance [3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13].”
• Conditional Teacher-student Learning (2019, unknown): “[30, 31], subspace-based [32, 33] and adversarial learning-based [34, 35] approaches.”