Results 11 to 20 of about 12,831 (261)
S-TRANSFORM AND GAUSSIAN MIXTURE MODEL FOR ACOUSTIC SCENE CLASSIFICATION
International Journal of Advances in Signal and Image Sciences, 2020 In this study, Acoustic Scene Classification (ASC) system is designed with the help of S-transform and Gaussian Mixture Model (GMM). The S-transform is an extension of continuous wavelet transform that combines the progressive resolution with phase ...
Santosh Kumar Srivastava
doaj +1 more source
Macro-Level Determinants of Entrepreneurship and Endogeneity Bias – A Methodological Contribution
M@n@gement, 2022 The eclectic theory of entrepreneurship has identified several macro-determinants of national entrepreneurial activities. Taking advantage of the availability of new databases, several recent empirical studies have sought to test these determinants in ...
Brahim Gaies, Adnane Maalaoui
doaj +1 more source
Revisiting hybrid and GMM-HMM system combination techniques [PDF]
2013 IEEE International Conference on Acoustics, Speech and Signal Processing, 2013 In this paper we investigate techniques to combine hybrid HMM-DNN (hidden Markov model - deep neural network) and tandem HMM-GMM (hidden Markov model - Gaussian mixture model) acoustic models using: (1) model averaging, and (2) lattice combination with Minimum Bayes Risk decoding.
Pawel Swietojanski +2 more
openaire +1 more source
Effect of advertising spending on operating and market performance of banks: empirical evidence from Bangladesh [PDF]
AJAR (Asian Journal of Accounting Research), 2022 Purpose - The purpose of the paper is to empirically explore the economic effect of advertising spending on the performance of banks on a sample consisting of all banks listed on the Dhaka Stock Exchange over the period spanning from 2011 to 2019. Design/
Md. Ibrahim Molla, Md. Kayes Bin Rahaman
doaj +1 more source
Text independent speaker recognition system using GMM [PDF]
2013 International Conference on Human Computer Interactions (ICHCI), 2013 The idea of the AUDIO SIGNAL PROCESSING (Speaker Recognition (4) Project) is to implement a recognizer using Matlab which can identify a person by processing his/her voice. The Matlab functions and scripts were all well documented and parameterized in order to be able to use them in the future. The basic goal of our project is to recognize and classify
S G Bagul, R. K. Shastri
openaire +1 more source
System GMM Estimation With A Small Sample [PDF]
, 2009 The support from the Spanish Ministry of Science and Innovation under project ECO2008-04837/ECON is gratefully acknowledged. The author acknowledges the support of the Barcelona GSE Research Network and of the Government of Catalonia.
Soto, Marcelo +2 more
+9 more sources
GMM Based Language Identification System Using Robust Features [PDF]
International Journal of Speech Technology, 2013 In this work, we propose new features for the GMM based spoken language identification system. A two stage approach is followed for extraction of the proposed new features. MFCCs and formants are extracted from huge corpus of all languages under consideration. In the first phase, MFCCs and formants are concatenated to form the feature vector.
Sadanandam Manchala, V. Kamakshi Prasad
openaire +2 more sources
Carbon Management, 2023 With the rise in global food insecurity, pollution, and wildlife extinction caused by climate change, development policies are now tailored toward addressing this quagmire.
Sulemana Mumuni +1 more
doaj +1 more source
Does Working Capital Management Influence Operating and Market Risk of Firms?
Risks, 2021 Extant empirical studies have predominantly focused on the nexus between working capital management (WCM) and corporate profitability. While there is a dearth of literature on the nexus between WCM and a firm’s risk, the present study examines Pakistani ...
Ahsan Akbar +4 more
doaj +1 more source
The Study of Malay’s Prosodic Features Impact on Classical Arabic Accents Recognition
IEEE Access, 2023 Modeling individual’s variation in speech pattern can be challenging in Automatic Speech Recognition (ASR). In Classical Arabic (CA) language, 20 Quranic accents are permitted for Quranic recitation.
Noor Jamaliah Ibrahim +4 more
doaj +1 more source