Cross-language knowledge transfer using multilingual deep neural network with shared hidden layers

By Jui-Ting Huang, Jinyu Li, Dong Yu, Li Deng, Yifan Gong. 2013

686 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing, Multimodal Learning

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

In Natural Language Processing

In Multimodal Learning

Citations in the corpus

Parameter-Efficient Transfer Learning for NLP (2019, background): “) (Collobert & Weston, 2008), multilingual models (Huang et al., 2013), semantic parsing (Peng et al.”
Learning multiple visual domains with residual adapters (2017, methodology): “MTL in DNNs has been applied to various problems ranging from natural language processing [8, 22], speech recognition [14] to computer vision [41, 42, 4].”
Multilingual Speech Recognition with a Single End-to-End Model (2017, background): “Most of the previous work on multilingual speech recognition has been limited to making the acoustic model (AM) multilingual [3, 4, 5, 6, 9, 10, 11, 12, 13].”
Unsupervised Pretraining Transfers Well Across Languages (2020, background): “Closer to our work, several works have shared the parameters of a neural network encoder, using feedforward networks [3, 1, 2] or LSTM [11].”
Libri-Light: A Benchmark for ASR with Limited or No Supervision (2019, neutral): “languages [5, 6] or pretraining using unsupervised objectives [7, 8].”
Deep Learning: Methods and Applications (2014, methodology): “The former is the un-normalized version of the cosine loss function used for training the DSSM model in [170] as described in Section 9.”
Efficient Parametrization of Multi-domain Deep Neural Networks (2018, methodology): “This paradigm is applied to various learning problems from natural language processing [6] and automated drug discovery [7] to speech recognition [12].”
Unsupervised Cross-lingual Representation Learning for Speech Recognition (2020, background): “This has been a long standing interest in the speech community [1, 2, 3, 4, 5, 6, 7] which includes systems able to transcribe multiple languages [8, 9, 10, 11, 12].”
Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics (2017, background): “Multi-task learning is prevalent in many applications of machine learning – from computer vision [2] to natural language processing [3] to speech recognition [4].”
A Survey on Deep Transfer Learning (2018, background): “[9] divide the network into two parts, the former part is the language-independent feature transform and the last layer is the language-relative classiﬁer.”
Deep Multi-task Representation Learning: A Tensor Factorisation Approach (2016, methodology): “For example, MNIST digit recognition is commonly used to 2 Related Work”
Beyond Shared Hierarchies: Deep Multitask Learning through Soft Layer Ordering (2017, background): “, 2016), speech (Huang et al., 2013; 2015; Seltzer and Droppo, 2013; Wu et al., 2015), and reinforcement learning (Devin et al.”
Multi-Task Learning as Multi-Objective Optimization (2018, background): “…processing (Collobert and Weston, 2008; Dong et al., 2015; Liu et al., 2015a; Luong et al., 2015; Hashimoto et al., 2017), speech processing (Huang et al., 2013; Seltzer and Droppo, 2013; Huang et al., 2015), and even seemingly unrelated domains over multiple modalities (Kaiser et al.,…”
Recent Advances in End-to-End Automatic Speech Recognition (2021, background): “Most hybrid multilingual works focus on building an acoustic model with shared hidden layers [70, 84, 100], while every language has its own lexicon model and language model.”
An Investigation of Deep Neural Networks for Multilingual Speech Recognition Training and Adaptation (2017, methodology): “Here, only the architecture in [3] and [8] is discussed and we denote this shared-hidden-layer multilingual DNN as SHL-MDNN following [3].”
A survey of deep neural network architectures and their applications (2017, methodology): “Moreover, the DNNs have been employed for tracking dialog state [53], transferring cros s-language knowledge [71], learning the filter banks [135], designing an automatic feature extraction systems from aud io [51], and speaker adaptive training (SAT) for acoustic modeling [114].”