Advanced recurrent network-based hybrid acoustic models for low resource speech recognition

Kang, Jian; Zhang, Weiqiang; Liu, Weiwei; Lu, Jia; Johnson, Michael T.

doi:10.1186/s13636-018-0128-6

Cited by 13 publications

(7 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Better expressiveness is shown in low-resource scenario on the condition that GRU has fewer parameters. Kang et al [24] proposed local BGRU with residual learning. All timedependency relationships were considered in a fixed local window.…”

Section: ) Recurrent Neural Networkmentioning

confidence: 99%

Acoustic Modeling Based on Deep Learning for Low-Resource Speech Recognition: An Overview

Kang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The polarization of world languages is becoming more and more obvious. Many languages, mainly endangered languages, are of low-resource attribute due to lack of information. Both language conservation and cultural heritage face important challenges. Therefore, speech recognition for lowresource scenario has become a hot topic in the field of speech. Based on the complex network structures and huge model parameters, deep learning has become a powerful science in the process of speech recognition, which has a broad and far-reaching significance for the study of low-resource speech recognition. Aiming at the characteristic of low resource, this paper reviews the history and research status of two kinds of acoustic models of deep learning neural networks and acoustic end-to-end structures. We further elaborate on several key techniques for improving performance in the two aspects of data and model training. There are two projects for low-resource languages introduced in this paper. The possible future developments are finally pointed out. These works provide some reference for computer speech and language processing.

show abstract

Section: ) Recurrent Neural Networkmentioning

confidence: 99%

Acoustic Modeling Based on Deep Learning for Low-Resource Speech Recognition: An Overview

Kang

Chen

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…[27] Speaker, Language, and Gender Identification LSTM Speech/Audio/ Music Analysis & Synthesis Garcia et al [28] Music Generation LSTM & GRU Madhok et al [29] Music Generation Stacked LSTM Song et al [30] Music tagging GRU Xie e al. [31] Speech emotion classification LSTM Kang et al [32] Speech recognition LSTM Nakyama et al [33] Audio Chord classification LSTM & GRU Chen et al [34] Voice detection GRU Human Action/Interact ion Recognition Sho et al [35] Human interaction recognition Hierarchichal LSTM Sho et al [36] Person-Person Action Recognition Concurrent LSTSM…”

Section: Role Of Gated Rnns In Various Application Domainsmentioning

confidence: 99%

Gated Recurrent Unit Architecture for Context-Aware Recommendations with improved Similarity Measures

Kala¹,

Nandhini²

2020

KSII TIIS

View full text Add to dashboard Cite

Recommender Systems (RecSys) have a major role in e-commerce for recommending products, which they may like for every user and thus improve their business aspects. Although many types of RecSyss are there in the research field, the state of the art RecSys has focused on finding the user similarity based on sequence (e.g. purchase history, moviewatching history) analyzing and prediction techniques like Recurrent Neural Network in Deep learning. That is RecSys has considered as a sequence prediction problem. However, evaluation of similarities among the customers is challenging while considering temporal aspects, context and multi-component ratings of the item-records in the customer sequences. For addressing this issue, we are proposing a Deep Learning based model which learns customer similarity directly from the sequence to sequence similarity as well as item to item similarity by considering all features of the item, contexts, and rating components using Dynamic Temporal Warping(DTW) distance measure for dynamic temporal matching and 2D-GRU (Two Dimensional-Gated Recurrent Unit) architecture. This will overcome the limitation of non-linearity in the time dimension while measuring the similarity, and the find patterns more accurately and speedily from temporal and spatial contexts. Experiment on the real world movie data set LDOS-CoMoDa demonstrates the efficacy and promising utility of the proposed personalized RecSys architecture.

show abstract

“…In hybrid acoustic modeling, various deep neural network models, such as feed-forward networks (fully connected deep neural network (DNN) [1][2][3][4][5][6][7][8] and convolutional neural network (CNN) [9][10][11][12][13][14][15][16]) and deep recurrent neural networks (conventional recurrent neural network (RNN) [17], long short-term memory (LSTM) [18][19][20][21][22], and gated recurrent unit (GRU) [23][24][25][26]) are examined for both low-and high-resource-languages speech recognition tasks. These neural network models have strong and weak sides.…”

Section: Introductionmentioning

confidence: 99%

“…The limitations of DNN and CNN models can be overcome using the recurrent neural network models, which have the ability to model long-term dependencies between speech features through unfolding for long time steps. However, the conventional RNN model suffers from vanishing and exploding gradients in the stochastic gradient decent (SGD) training process [19,20,22]. These limitations of RNN model can be reduced using advanced recurrent neural network models (LSTM [12,19,22] and GRU [24,25]).…”

Section: Introductionmentioning

confidence: 99%

“…Moreover, several advanced neural network acoustic models have been developed through the combination of various feed-forward and recurrent neural network models for acquiring the best quality of the individual models using four different model combination paradigms. First, train the individual neural network acoustic models independently, and then combine the outputs such as a lattice-based system combination approach [12,20]. Second, train the individual neural network acoustic models separately, and then combine these using the combiner layer [35].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition

Fantaye

Hailu

2020

Computers

View full text Add to dashboard Cite

Deep neural networks (DNNs) have shown a great achievement in acoustic modeling for speech recognition task. Of these networks, convolutional neural network (CNN) is an effective network for representing the local properties of the speech formants. However, CNN is not suitable for modeling the long-term context dependencies between speech signal frames. Recently, the recurrent neural networks (RNNs) have shown great abilities for modeling long-term context dependencies. However, the performance of RNNs is not good for low-resource speech recognition tasks, and is even worse than the conventional feed-forward neural networks. Moreover, these networks often overfit severely on the training corpus in the low-resource speech recognition tasks. This paper presents the results of our contributions to combine CNN and conventional RNN with gate, highway, and residual networks to reduce the above problems. The optimal neural network structures and training strategies for the proposed neural network models are explored. Experiments were conducted on the Amharic and Chaha datasets, as well as on the limited language packages (10-h) of the benchmark datasets released under the Intelligence Advanced Research Projects Activity (IARPA) Babel Program. The proposed neural network models achieve 0.1–42.79% relative performance improvements over their corresponding feed-forward DNN, CNN, bidirectional RNN (BRNN), or bidirectional gated recurrent unit (BGRU) baselines across six language collections. These approaches are promising candidates for developing better performance acoustic models for low-resource speech recognition tasks.

show abstract

Advanced recurrent network-based hybrid acoustic models for low resource speech recognition

Cited by 13 publications

References 35 publications

Acoustic Modeling Based on Deep Learning for Low-Resource Speech Recognition: An Overview

Acoustic Modeling Based on Deep Learning for Low-Resource Speech Recognition: An Overview

Gated Recurrent Unit Architecture for Context-Aware Recommendations with improved Similarity Measures

Advanced Convolutional Neural Network-Based Hybrid Acoustic Models for Low-Resource Speech Recognition

Contact Info

Product

Resources

About