Robust Feature Extraction from AD-HOC Microphones for Meeting Diarization

Sharma, Dushyant; Nour-Eldin, Amr H.; Harding, Philip J.; Karimian-Azari, Sam; Naylor, Patrick A.

doi:10.1109/iwaenc.2018.8521339

Cited by 2 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is speaker diarization technology by Sharma et al (2018) as a technology for easily reviewingthemeetingcontents.However,thesetechnologiesmayaffectvoicerecognitionperformance duetoreverberationandnoisegeneratedinthemeetingroom.…”

Section: Related Workmentioning

confidence: 99%

Implementation of an Interactive Information Sharing System for Disaster Measure Operation

Nakai

Ishida

2020

International Journal of Mobile Computing and Multimedia Communications

View full text Add to dashboard Cite

This study develops an interactive information sharing system for disaster measure operations, called “HyperRem.” It consists of the HyperRem-Master and the HyperRem-Node. The HyperRem-Master aggregates information held by meeting participants and visualizes it on a large display. The HyperRem-Node transmits information to the HyperRem-Master by flicking operation from mobile terminals and laptops owned by meeting participants. HyperRem saves screen states visualized on a large display to a database in chronological order, and the saved screen states can be reused. A reuse function and a playback function are implemented to reuse past screen states. The reuse function enables users to resume meetings by restoring past meeting contents to the large display. The playback function provides a review function for past meetings to absentees via a dedicated web page. The operability, functionality, effectiveness, and applicability of HyperRem were confirmed in an evaluation experiment with 10 subjects. The survey results of all five measures revealed an overwhelmingly positive response.

show abstract

Section: Related Workmentioning

confidence: 99%

Implementation of an Interactive Information Sharing System for Disaster Measure Operation

Nakai

Ishida

2020

International Journal of Mobile Computing and Multimedia Communications

View full text Add to dashboard Cite

show abstract

“…One of the output nodes estimates the POLQA score and the second node estimates the Mean Voice activity Posterior (MVP). The MVP is obtained by running a simple VAD from [34] on the clean speech used in the synthesis of the training data (described in more detail in Section III). The VAD outputs a posterior probability of the frame being voiced and these scores are averaged over the context window used for the RNN model, resulting in a mean voice activity posterior, which becomes the target of the second output of the RNN model.…”

Section: Recurrent Neural Network Modelmentioning

confidence: 99%

Non-Intrusive POLQA Estimation of Speech Quality using Recurrent Neural Networks

Sharma

Hogg

Wang

et al. 2019

2019 27th European Signal Processing Conference (EUSIPCO)

Self Cite

View full text Add to dashboard Cite

Estimating the quality of speech without the use of a clean reference signal is a challenging problem, in part due to the time and expense required to collect sufficient training data for modern machine learning algorithms. We present a novel, non-intrusive estimator that exploits recurrent neural network architectures to predict the intrusive POLQA score of a speech signal in a short time context. The predictor is based on a novel compressed representation of modulation domain features, used in conjunction with static MFCC features. We show that the proposed method can reliably predict POLQA with a 300 ms context, achieving a mean absolute error of 0.21 on unseen data. The proposed method is trained using English speech and is shown to generalize well across unseen languages. The neural network also jointly estimates the mean voice activity detection (VAD) with an F1 accuracy score of 0.9, removing the need for an external VAD.

show abstract

Robust Feature Extraction from AD-HOC Microphones for Meeting Diarization

Cited by 2 publications

References 16 publications

Implementation of an Interactive Information Sharing System for Disaster Measure Operation

Implementation of an Interactive Information Sharing System for Disaster Measure Operation

Non-Intrusive POLQA Estimation of Speech Quality using Recurrent Neural Networks

Contact Info

Product

Resources

About