A de-noising algorithm for voice recognition with low SNR

2016 ◽  
Author(s):  
Hua-An Zhao ◽  
Kazuma Uchida
Keyword(s):  
Voice Recognition ◽  
Low Snr

The effect of speech idiosyncrasies on voice recognition: Is it a laughing matter?

1997 ◽  
Author(s):  
Craig B. Neely ◽  
Jeffrey R. Wilson ◽  
Brian H. Bornstein
Keyword(s):  
Voice Recognition

Toward speaker independent voice recognition

1982 ◽  
Author(s):  
Gary K. Poock ◽  
Norman D. Schwalm ◽  
Ellen F. Roland
Keyword(s):  
Voice Recognition ◽  
Speaker Independent

Initial validation of voice recognition interpretation methodology

2011 ◽  
Author(s):  
Jeffrey A. Daniels ◽  
Maria J. Amores ◽  
Jennifer Haist ◽  
Susan Chamberlain ◽  
Karianne Bilsky ◽  
...  
Keyword(s):  
Voice Recognition ◽  
Initial Validation

Lampu Sein Helm Sepeda Berbasis Voice Recognition

2019 ◽  
Vol 11 (01) ◽  
pp. 20-25
Author(s):  
Indra Saputra ◽  
Parulian Silalahi ◽  
Bayu Cahyawan ◽  
Imam Akbar
Keyword(s):  
Voice Recognition ◽  
Driving Safety ◽  
Bicycle Helmet ◽  
Turn Signal ◽  
Voice Command ◽  
The Voice ◽  
Indicator Signal

Bicycles are not equipped with the turn signal. For driving safety, a bicycle helmet with a turn signal is designed with voice rrecognition. It is using the Arduino Nano as a controller to control the ON and OFF of turn signal lights with voice commands. This device uses a Voice Recognition sensor and microphone that placed on a bicycle helmet. When the voice command is mentioned in the microphone, the Voice Recognition sensor will detect the command specified, the sensor will automatically read and send a signal to Arduino, then the turn signal will light up as instructed, the Arduino on the helmet will send an indicator signal via the Bluetooth Module. The device is able to detect sound with a percentage of 80%. The tool can work with a distance of <2 meters with noise <71 db.

Items Searching in Factory Warehouse Using Arduino Module

2019 ◽  
Vol 1 (1) ◽  
pp. 1-14
Author(s):  
Tan Liong Ching ◽  
Nureize Binti Arbaiy
Keyword(s):  
Inventory Management ◽  
Liquid Crystal Display ◽  
Light Emitting Diode ◽  
Storage System ◽  
Voice Recognition ◽  
Inventory System ◽  
Search Process ◽  
Light Emitting ◽  
Recognition Function ◽  
Light Function

The smart store system (F3 Storage System) provides an inventory system function, and is supported by voice recognition for items searching purpose in the warehouse. This system is aimed to improve effectiveness in item searching process for the warehouse management. An inventory system structures is employed in this system to enable items management. Voice recognition facility helps the worker to search item in an effective way. Worker can use voice recognition function to search the item in the warehouse, and searched information of the item will be displayed in the liquid crystal display (LCD) screen. Meanwhile, the location of the item will be physically indicated by the light emitting diode (LED) light function. The developed system also contains a barcode system to enhance the process of scheduling warehouse activity. Such facilities will enhance the capabilities of existing inventory management systems in warehouses. Prototyping model is used to assist project development. Arduino technology is used to enable integrated hardware and software to read data or input. With Arduino technology, traditional search items by using text and search functionality are enhanced to allow speech functionality. This functionality makes the search process faster and more efficient.

ANALYSIS OF VOICE CUES IN RECOGNITION OF SARCASM

2019 ◽  
Vol 12 ◽  
Author(s):  
Basavaraj N Hiremath ◽  
Malini M Patilb
Keyword(s):  
Feature Extraction ◽  
Computer Program ◽  
Principle Component Analysis ◽  
Voice Recognition ◽  
Component Analysis ◽  
Recognition System ◽  
Principle Component ◽  
Whole Process ◽  
The Voice

The voice recognition system is about cognizing the signals, by feature extraction and identification of related parameters. The whole process is referred to as voice analytics. The paper aims at analysing and synthesizing the phonetics of voice using a computer program called “PRAAT”. The work carried out in the paper also supports the analysis of voice segmentation labelling, analyse the unique features of voice cues, understanding physics of voice, further the process is carried out to recognize sarcasm. Different unique features identified in the work are, intensity, pitch, formants related to read, speak, interactive and declarative sentences by using principle component analysis.

scholarly journals Low-Frequency Expansion Approach for Seismic Data Based on Compressed Sensing in Low SNR

2021 ◽  
Vol 11 (11) ◽  
pp. 5028
Author(s):  
Miaomiao Sun ◽  
Zhenchun Li ◽  
Yanli Liu ◽  
Jiao Wang ◽  
Yufei Su
Keyword(s):  
Reflection Coefficient ◽  
Compressed Sensing ◽  
Objective Function ◽  
Low Frequency ◽  
Original Data ◽  
Seismic Exploration ◽  
High Signal ◽  
Inversion Process ◽  
Frequency Information ◽  
Low Snr

Low-frequency information can reflect the basic trend of a formation, enhance the accuracy of velocity analysis and improve the imaging accuracy of deep structures in seismic exploration. However, the low-frequency information obtained by the conventional seismic acquisition method is seriously polluted by noise, which will be further lost in processing. Compressed sensing (CS) theory is used to exploit the sparsity of the reflection coefficient in the frequency domain to expand the low-frequency components reasonably, thus improving the data quality. However, the conventional CS method is greatly affected by noise, and the effective expansion of low-frequency information can only be realized in the case of a high signal-to-noise ratio (SNR). In this paper, well information is introduced into the objective function to constrain the inversion process of the estimated reflection coefficient, and then, the low-frequency component of the original data is expanded by extracting the low-frequency information of the reflection coefficient. It has been proved by model tests and actual data processing results that the objective function of estimating the reflection coefficient constrained by well logging data based on CS theory can improve the anti-noise interference ability of the inversion process and expand the low-frequency information well in the case of a low SNR.

Sign in / Sign up

Export Citation Format

Share Document