AN EVALUATION OF SOME FACTORS AFFECTING ACCURACY OF THE VIETNAMESE KEYWORD SPOTTING SYSTEM

2020 ◽  
pp. 33-43
Author(s):  
Xuan
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Call Center ◽  
Smart Home ◽  
Far Field ◽  
Keyword Spotting ◽  
Factors Affecting ◽  
Testing Environment ◽  
Call Routing ◽  
Voice Control

Keyword spotting (KWS) is one of the important systems on speech applications, such as data mining, call routing, call center, customer-controlled smartphone, smart home systems with voice control, etc. With the goals of researching some factors affecting the Vietnamese Keyword spotting system, we study the combination architecture of CNN (Convolutional Neural Networks)-RNN (Recurrent Neural Networks) on both clean and noise environments with 2 distance speaker cases: 1m and 2m. The obtained results show that the noise trained models are better performance than clean trained models in any (clean or noise) testing environment. The results in this far-field experiment suggest to us how to choose the suitable distance of the recording microphones to the speaker so that there is no redundancy of data with the contexts considered to be the same. 

scholarly journals Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

2017 ◽  
Author(s):  
Sercan Ö. Arık ◽  
Markus Kliegl ◽  
Rewon Child ◽  
Joel Hestness ◽  
Andrew Gibiansky ◽  
...  
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Keyword Spotting ◽  
Small Footprint

Levenshtein Augmentation Improves Performance of SMILES Based Deep-Learning Synthesis Prediction

2020 ◽  
Author(s):  
Dean Sumner ◽  
Jiazhen He ◽  
Amol Thakkar ◽  
Ola Engkvist ◽  
Esben Jannik Bjerrum
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Recurrent Neural Networks ◽  
Data Augmentation ◽  
State Of The Art ◽  
Sequence Similarity ◽  
Learning Models ◽  
Underlying Network

<p>SMILES randomization, a form of data augmentation, has previously been shown to increase the performance of deep learning models compared to non-augmented baselines. Here, we propose a novel data augmentation method we call “Levenshtein augmentation” which considers local SMILES sub-sequence similarity between reactants and their respective products when creating training pairs. The performance of Levenshtein augmentation was tested using two state of the art models - transformer and sequence-to-sequence based recurrent neural networks with attention. Levenshtein augmentation demonstrated an increase performance over non-augmented, and conventionally SMILES randomization augmented data when used for training of baseline models. Furthermore, Levenshtein augmentation seemingly results in what we define as <i>attentional gain </i>– an enhancement in the pattern recognition capabilities of the underlying network to molecular motifs.</p>

Sign in / Sign up

Export Citation Format

Share Document