Refinement of Convolutional Neural Network Based Cell Nuclei Detection Using Bayesian Inference

Kowal, Marek; Korbicz, Józef

doi:10.1109/embc.2019.8857950

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our research, self-similarity matrices are constructed based on acoustic parameters differentiating between neutral speech and produced by the Lombard effect. The resulting graphical representations are derived from the differences between acoustic characteristics of the non-Lombard and Lombard speech signals and are used as an input to a convolutional neural network (CNN), widely used in image classification (Bernardo et al, 2021;Kowal and Korbicz, 2019). It should be pointed out that using self-similarity matrices is a novel approach to investigating the Lombard effect phenomenon in uttered speech.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Lombard effect based on a machine learning approach

Korvel,

Treigys,

Kąkol

et al. 2023

International Journal of Applied Mathematics and Computer Scien

View full text Add to dashboard Cite

The Lombard effect is an involuntary increase in the speaker's pitch, intensity, and duration in the presence of noise. It makes it possible to communicate in noisy environments more effectively. This study aims to investigate an efficient method for detecting the Lombard effect in uttered speech. The influence of interfering noise, room type, and the gender of the person on the detection process is examined. First, acoustic parameters related to speech changes produced by the Lombard effect are extracted. Mid-term statistics are built upon the parameters and used for the self-similarity matrix construction. They constitute input data for a convolutional neural network (CNN). The self-similarity-based approach is then compared with two other methods, i.e., spectrograms used as input to the CNN and speech acoustic parameters combined with the k-nearest neighbors algorithm. The experimental investigations show the superiority of the self-similarity approach applied to Lombard effect detection over the other two methods utilized. Moreover, small standard deviation values for the selfsimilarity approach prove the resulting high accuracies.

show abstract

Section: Introductionmentioning

confidence: 99%

Investigation of the Lombard effect based on a machine learning approach

Korvel,

Treigys,

Kąkol

et al. 2023

International Journal of Applied Mathematics and Computer Scien

View full text Add to dashboard Cite

show abstract

Nuclei and glands instance segmentation in histology images: a narrative review

2022

View full text Add to dashboard Cite

Medical informatization of management system for admission office under convolutional neural network

Wang

et al. 2021

Expert Systems

View full text Add to dashboard Cite

The study aims to construct a client/server model of a three‐tier architecture based on the convolutional neural network (CNN), which is responsible for information management in admission office, including eight aspects of the registration management, admission management, prepayment management, inpatient charge management, settlement management, report statistics management, information query management, and help management. The test results of the system show that the management system constructed can run 48 h trouble‐free for registration services, no‐fee discharge services, inpatient charge services, and settlement services, and the average response time of the system is less than 10 s. The management system constructed for the admission office realizes the medical informatization, and heightens the work efficiency of relevant workers.

show abstract

Refinement of Convolutional Neural Network Based Cell Nuclei Detection Using Bayesian Inference

Cited by 3 publications

References 24 publications

Investigation of the Lombard effect based on a machine learning approach

Investigation of the Lombard effect based on a machine learning approach

Nuclei and glands instance segmentation in histology images: a narrative review

Medical informatization of management system for admission office under convolutional neural network

Contact Info

Product

Resources

About