A robust algorithm for word boundary detection in the presence of noise

Junqua, Jean‐Claude; Mak, Brian; Reaves, B.

doi:10.1109/89.294354

Cited by 141 publications

(85 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…More recently, there has been some interest in robustness to noise, due to the advent of cellular phones and handsfree headsets. For instance, there is the work of Junqua et al [1] which presents a number of adaptive energy-based techniques, the work of Huang and Yang [2], which uses This work was done while the author was at the MIT Media Laboratory a spectral entropy measure to pick out voiced regions, and later the work of Wu and Lin [3], which extends the work of Junqua et. al by looking at multiple bands and using a neural network to learn the appropriate thresholds.…”

Section: Introductionmentioning

confidence: 99%

A linked-HMM model for robust voicing and speech detection

Basu

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).

View full text Add to dashboard Cite

We present a novel method for simultaneous voicing and speech detection based on a linked-HMM architecture, with robust features that are independent of the signal energy. Because this approach models the change in dynamics between speech and non-speech regions, it is robust to low sampling rates, significant levels of additive noise, and large distances from the microphone. We demonstrate the performance of our method in a variety of testing conditions and also compare it to other methods reported in the literature.

show abstract

Section: Introductionmentioning

confidence: 99%

A linked-HMM model for robust voicing and speech detection

Basu

2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).

View full text Add to dashboard Cite

show abstract

“…When training a classifier, the classifier creates boundaries in the features space between the investigated classes. Inaccurate detection of an event can be a common cause of errors in automatic classification [12].…”

Section: Neural Network Based Classificationmentioning

confidence: 99%

Real-time Distributed Fiber Optic Sensor for Security Systems: Performance, Event Classification and Nuisance Mitigation

2012

View full text Add to dashboard Cite

Abstract:The success of any perimeter intrusion detection system depends on three important performance parameters: the probability of detection (POD), the nuisance alarm rate (NAR), and the false alarm rate (FAR). The most fundamental parameter, POD, is normally related to a number of factors such as the event of interest, the sensitivity of the sensor, the installation quality of the system, and the reliability of the sensing equipment. The suppression of nuisance alarms without degrading sensitivity in fiber optic intrusion detection systems is key to maintaining acceptable performance. Signal processing algorithms that maintain the POD and eliminate nuisance alarms are crucial for achieving this. In this paper, a robust event classification system using supervised neural networks together with a level crossings (LCs) based feature extraction algorithm is presented for the detection and recognition of intrusion and non-intrusion events in a fence-based fiber-optic intrusion detection system. A level crossings algorithm is also used with a dynamic threshold to suppress torrential rain-induced nuisance alarms in a fence system. Results show that rain-induced nuisance alarms can be suppressed for rainfall rates in excess of 100 mm/hr with the simultaneous detection of intrusion events. The use of a level crossing based detection and novel classification algorithm is also presented for a buried pipeline fiber optic intrusion detection system for the suppression of nuisance events and discrimination of intrusion events. The sensor employed for both types of systems is a distributed bidirectional fiber-optic Mach-Zehnder (MZ) interferometer.

show abstract

“…With this technique, both the energy and zero-crossing rate of the signal are used to define the end points of an utterance. This technique is simpler to use than more advanced techniques, such as those specified by Lamel, Rabiner, Rosenburg, and Wilpon (1981); Wilpon and Rabiner (1987); Savoji (1989); and more recently by Junqua, Mak, and Reaves (1994). Some modifications were made to improve performance under the conditions used in our SVT studies at the Hearing Health Care Research Unit.…”

Section: Requirementsmentioning

confidence: 99%

A vocal response time system for use with sentence verification tasks

James

1996

Behavior Research Methods, Instruments, & Computers

View full text Add to dashboard Cite

A robust algorithm for word boundary detection in the presence of noise

Cited by 141 publications

References 7 publications

A linked-HMM model for robust voicing and speech detection

A linked-HMM model for robust voicing and speech detection

Real-time Distributed Fiber Optic Sensor for Security Systems: Performance, Event Classification and Nuisance Mitigation

A vocal response time system for use with sentence verification tasks

Contact Info

Product

Resources

About