Enhanced voice activity detection using acoustic event detection and classification

Cho, Namgook; Kim, Eunkyoung

doi:10.1109/tce.2011.5735502

Cited by 36 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For instance, the images that contained face expression of customers require having the whole face unit detected and segmented. On the other hand, the certain time range of signals needs Voice Activity Detector (VAD) to identify the segments of time range that contain the existence of human voice (Cho, 2011). 3.…”

Section: Automated Emotion Recognition Systemmentioning

confidence: 99%

Customer Satisfaction through Technological Integration

Seng

Ang

Shing³

2016

International Journal of Technology and Educational Marketing

View full text Add to dashboard Cite

This paper presents a review of automated technology integrations for organizations to assess their customer satisfaction levels. The paper also includes a comparison of the common resources that are used to measure customer satisfaction. The main part of the paper subsequently describes the related concerns and challenges that are faced by the business company to realize customer satisfactions. This paper presents a review of automated technology integrations for organizations to assess their customer satisfaction. These components can be integrated into communication tools to solve the existing problems efficiently, and improve the way of assessing customer satisfaction. The limitations or challenges of current approaches in technology related ways to realize the satisfactions are also discussed. The end of the paper gives recommendations and solutions to show the possible ways in solving the existing problems and improving the way of assessing customer satisfaction by integrating the appropriate technology.

show abstract

Section: Automated Emotion Recognition Systemmentioning

confidence: 99%

Customer Satisfaction through Technological Integration

Seng

Ang

Shing³

2016

International Journal of Technology and Educational Marketing

View full text Add to dashboard Cite

show abstract

“…Similar work by Namgook and Kim [22] developed voice detection and classification modules integrating a total of 202 minutes of audio containing wood, metal, door slam and speech sounds via Gaussian mixture models (GMM) and support vector machines (SVM). GMM performed well giving an accuracy of 98.72% for "door-slamming + speech" activity compared to 88.3% for the closest presented case of "Door-closing DC + Traffic TF" in the proposed methodology.…”

Section: Benchmarking With Previous Workmentioning

confidence: 99%

“…Block diagram of the classification of non-silent activity segments via an autoregressive neural classifier (NARX) with directional audio as exogenous data. The Summation of Energy features are actively utilized in sound synthesis research as reported by Portelo et al[22] …”

mentioning

confidence: 99%

Application of acoustic directional data for audio event recognition via HMM/CRF in perimeter surveillance systems

Yusuf¹,

Brown

Mackinnon³

2015

Robotics and Autonomous Systems

View full text Add to dashboard Cite

Audio event detection (AED) and recognition is a signal processing and analysis domain used in a wide range of applications including surveillance, home automation and behavioral assessment. The field presents numerous challenges to the current state-of-the-art due to its highly nonlinear nature. High false alarm rates (FARs) in such applications particularly limit the capabilities of vision-based perimeter monitoring systems by inducing high operator dependence. On the other hand, conventional fence-based vibration detectors and pressure-driven "taut wires" offer high sensitivity at the cost of a high FAR due to debris, animals and weather. This work reports an audio event identification methodology implemented as a test-bed system for a surveillance application to reduce FAR, maximize blind-spot coverage and improve audio event classification accuracy. The first phase utilizes a nonlinear autoregressive classifier to locate and classify discrete audio events via an exogenous sound direction variable to improve classifier confidence. The second phase implements a time-series-based system to recognize various audio activity groups from nominal everyday sound events such as traffic and muffled speech. The discretely labeled data is thus trained with HMM and Conditional Random Field classifiers and reports a substantial improvement in classification accuracies of indoor human activities.

show abstract