Multi-basis adaptive neural network for rapid adaptation in speech recognition

By Chunyang Wu, Mark John Francis Gales. 2015

74 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. Li Deng
4. Tara N. Sainath
5. Yifan Gong
6. Khe Chai Sim
7. Bo Li
8. Arun Narayanan

In Signal Processing

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

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].”
• Speaker-Invariant Training Via Adversarial Learning (2018, methodology): “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].”
• Speaker-Aware Neural Network Based Beamformer for Speaker Extraction in Speech Mixtures (2017, methodology): “The most common approaches include using speaker representation as additional input feature [16, 17, 18] or adapting part of the parameters for each speaker [19, 20, 21].”
• Recent progresses in deep learning based acoustic models (2017, background): “Therefore, the number of bases in CAT is usually constrained to few [113], [114].”
• Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks (2019, methodology): “These techniques include, Cluster Adaptive Training (CAT) [12], context adaptive training [13], and multi-basis adaptive training [14].”
• Stimulated Deep Neural Network for Speech Recognition (2016, methodology): “In the DNN-CAT [11, 12] and the multi-basis adaptive neural network [13] models, speaker-dependent interpolation weights are introduced to combine different DNN modules to handle the acoustic distortions.”
• 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].”
• Domain Adaptation Using Factorized Hidden Layer for Robust Automatic Speech Recognition (2018, background): “…have been previously studied, including i-vector feature augmentation [19, 20], speaker-code adaptation [21], cluster adaptive training (CAT) [22, 23], factorized hidden layer [9], learning hidden unit contribution (LHUC) [24], singular value decomposition based subspace adaptation [25] and low…”
• An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation (2017, background): “Similar approaches have been proposed independently in [12] and [13].”
• Factorized Hidden Layer Adaptation for Deep Neural Network Based Acoustic Modeling (2016, methodology): “In cluster adaptive training (CAT) [22], [23], a set of bases are estimated during training and followed by an interpolation vector estimation to combine these bases during testing.”