Novel Front-End Features Based on Neural Graph Embeddings for DNN-HMM and LSTM-CTC Acoustic Modeling

2016 ◽  
Author(s):  
Yuzong Liu ◽  
Katrin Kirchhoff
Keyword(s):  
Acoustic Modeling ◽  
Graph Embeddings ◽  
Front End

Performance Analysis of various Front-end and Back End Amalgamations for Noise-robust DNN-based ASR

2020 ◽  
Vol 13 ◽  
Author(s):  
Mohit Dua ◽  
Pawandeep Singh Sethi ◽  
Vinam Agrawal ◽  
Raghav Chawla
Keyword(s):  
Feature Extraction ◽  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Gaussian Mixture ◽  
Performance Comparison ◽  
Acoustic Modeling ◽  
Extraction Techniques ◽  
Front End ◽  
Noise Robust ◽  
Asr System

Introduction: An Automatic Speech Recognition (ASR) system enables to recognize the speech utterances and thus can be used to convert speech into text for various purposes. These systems are deployed in different environments such as clean or noisy and are used by all ages or types of people. These also present some of the major difficulties faced in the development of an ASR system. Thus, an ASR system need to be efficient, while also being accurate and robust. Our main goal is to minimize the error rate during training as well as testing phases, while implementing an ASR system. Performance of ASR depends upon different combinations of feature extraction techniques and back-end techniques. In this paper, using a continuous speech recognition system, the performance comparison of different combinations of feature extraction techniques and various types of back-end techniques has been presented Methods: Hidden Markov Models (HMMs), Subspace Gaussian Mixture Models (SGMMs) and Deep Neural Networks (DNNs) with DNN-HMM architecture, namely Karel's, Dan's and Hybrid DNN-SGMM architecture are used at the back-end of the implemented system. Mel frequency Cepstral Coefficient (MFCC), Perceptual Linear Prediction (PLP), and Gammatone Frequency Cepstral coefficients (GFCC) are used as feature extraction techniques at the front-end of the proposed system. Kaldi toolkit has been used for the implementation of the proposed work. The system is trained on the Texas Instruments-Massachusetts Institute of Technology (TIMIT) speech corpus for English language Results: The experimental results show that MFCC outperforms GFCC and PLP in noiseless conditions, while PLP tends to outperform MFCC and GFCC in noisy conditions. Furthermore, the hybrid of Dan's DNN implementation along with SGMM performs the best for the back-end acoustic modeling. The proposed architecture with PLP feature extraction technique in the front end and hybrid of Dan's DNN implementation along with SGMM at the back end outperforms the other combinations in a noisy environment. Conclusion: Automatic Speech recognition has numerous applications in our lives like Home automation, Personal assistant, Robotics etc. It is highly desirable to build an ASR system with good performance. The performance Automatic Speech Recognition is affected by various factors which include vocabulary size, whether system is speaker dependent or independent, whether speech is isolated, discontinuous or continuous, adverse conditions like noise. The paper presented an ensemble architecture that uses PLP for feature extraction at the front end and a hybrid of SGMM + Dan's DNN in the backend to build a noise robust ASR system Discussion: The presented work in this paper discusses the performance comparison of continuous ASR systems developed using different combinations of front-end feature extraction (MFCC, PLP, and GFCC) and back-end acoustic modeling (mono-phone, tri-phone, SGMM, DNN and hybrid DNN-SGMM) techniques. Each type of front-end technique is tested in combination with each type of back-end technique. Finally, it compares the results of the combinations thus formed, to find out the best performing combination in noisy and clean conditions

Low-voltage BIMOS AM front-end amplifier

1990 ◽  
Vol 137 (1) ◽  
pp. 57 ◽  
Author(s):  
M. Steyaert ◽  
Z. Chang
Keyword(s):  
Low Voltage ◽  
Front End

Becoming the Nuclear-Front-End

2017 ◽  
Vol 47 (189) ◽  
Author(s):  
Patrick Schukalla
Keyword(s):  
Nuclear Reactor ◽  
Chemical Elements ◽  
High Technology ◽  
Power Production ◽  
Uranium Mining ◽  
Nuclear Industry ◽  
Current State ◽  
Front End ◽  
Production And Consumption ◽  
Uranium Exploration

Uranium mining often escapes the attention of debates around the nuclear industries. The chemical elements’ representations are focused on the nuclear reactor. The article explores what I refer to as becoming the nuclear front – the uranium mining frontier’s expansion to Tanzania, its historical entanglements and current state. The geographies of the nuclear industries parallel dominant patterns and the unevenness of the global divisions of labour, resource production and consumption. Clearly related to the developments and expectations in the field of atomic power production, uranium exploration and the gathering of geological knowledge on resource potentiality remains a peripheral realm of the technopolitical perceptions of the nuclear fuel chain. Seen as less spectacular and less associated with high-technology than the better-known elements of the nuclear industry the article thus aims to shine light on the processes that pre-figure uranium mining by looking at the example of Tanzania.

Análisis de la aplicación de pruebas funcionales y pruebas de usabilidad de software en el desarrollo de sistemas web

2019 ◽  
Vol 3 (3.4.) ◽  
pp. 180-190
Author(s):  
Natalia Patricia Layedra Larrea ◽  
Marco Vinicio Ramos Valencia ◽  
Blanca Faustina Hidalgo Ponce ◽  
Angela Elizabeth Samaniego Orozco
Keyword(s):  
Front End ◽  
El Sistema

El objetivo general del presente trabajo es analizar la aplicación de pruebas funcionales y pruebas de usabilidad en sistemas web. Para aplicar dichas pruebas se desarrolló un sistema web para la gestión de reuniones eclesiásticas para la Iglesia Bíblica Riobamba. El sistema fue desarrollado utilizando la metodología de desarrollo SCRUM, que permitió realizar un análisis de los requerimientos levantados tanto en prioridad de desarrollo como en el tiempo en que se realiza cada uno; además, se utilizó la tecnología AngularJS para el front end, mientras que para el back end se trabajó con el lenguaje de programación JAVA en el entorno de desarrollo Netbeans 8.2, y servicios RestFULL que permiten la conexión entre el front end y el back end. Finalmente, para la gestión de la base de datos se utilizó PostgreSQL. Sobre el sistema se han ejecutado pruebas de funcionamiento y usabilidad. Para obtener los resultados de la usabilidad del sistema se aplicó una encuesta de usabilidad a un grupo de 20 usuarios con distintos roles dentro del sistema, de los cuales el 90.14% manifestaron que pudieron usarlo fácilmente. Las pruebas de funcionamiento se aplicaron en el módulo de autenticación de usuarios, considerando que existen varios roles. Como resultado de las pruebas de funcionamiento se obtuvo un funcionamiento adecuado del módulo, en base a lo esperado por los usuarios.

Study on Improving Overall Efficiency of Front-end Power Supplies by Employing Method of Surge Energy Recycling

2012 ◽  
Vol 132 (7) ◽  
pp. 684-690 ◽  
Author(s):  
Toshikazu Okubo ◽  
Hiroyuki Shoji ◽  
Hideho Yamamura ◽  
Shinobu Irikura ◽  
Naoki Maru
Keyword(s):  
Power Supplies ◽  
Front End ◽  
Overall Efficiency

SUCCESS FACTORS IN THE FRONT END OF INNOVATION

2018 ◽  
Vol 2018 ◽  
pp. 926-926
Author(s):  
Alexander Vélez ◽  
◽  
Jose M Barrutia ◽  
Carmen Etxebarria
Keyword(s):  
Success Factors ◽  
Front End
Sign in / Sign up

Export Citation Format

Share Document