Evaluating MFCC-based speaker identification systems with data envelopment analysis

被引:6
|
作者
Ozcan, Zubeyir [1 ]
Kayikcioglu, Temel [1 ]
机构
[1] Karadeniz Tech Univ, Fac Engn, Dept Elect & Elect Engn, Trabzon, Turkey
关键词
Speaker recognition evaluation; Multi-criteria decision making; Data envelopment analysis; Speaker identification; MFCC features; MCDM; EFFICIENCY; CLASSIFICATION; RECOGNITION; SELECTION; MACHINES; RANKING;
D O I
10.1016/j.eswa.2020.114448
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The concept of the efficiency of speaker recognition systems varies in the literature. Although many authors have defined efficiency as recognition accuracy, others have defined it as low energy consumption, memory storage, or computational burden. In our study, for a novel approach, speaker recognition was evaluated following a multi-criteria decision-making approach in two stages. First, speaker identification based on Melfrequency cepstrum coefficients (MFCC) was conducted for various parameters and methods, including number of speakers, number of MFCCs, test speech duration, training utterance length and the various classifiers. Classification metrics, memory storage, testing, and training time of the trials were measured as well, and the performance of the trials was examined for each criterion. Verifying the literature, the study revealed that no parameters or methods achieved the best performance for all criteria. In the second stage, a multi-criteria efficiency analysis, as suggested in the literature, was conducted according to various application scenarios. By using data envelopment analysis, the efficiency of trials according to the scenarios was determined. After ranking the efficiency scores, it was revealed that the best solution was task-dependent. From the perspective of classifiers, artificial neural networks outperformed the others considering benefits to cost; however, some of their costs were high, whereas the other classifiers provided the best solutions in light of cost criteria. Last, the number of MFCCs was the least effective parameter for efficiency. Altogether, the findings indicate that the efficiency of a speaker identification system cannot be defined as recognition accuracy, memory storage, testing time or training time but as a function of those criteria.
引用
收藏
页数:13
相关论文
共 50 条
  • [41] Evaluating Airline Service Quality by Data Envelopment Analysis
    Higgins, Kevin M.
    Lawphongpanich, Siriphong
    Mahoney, John F.
    Yin, Yafeng
    TRANSPORTATION RESEARCH RECORD, 2008, (2052) : 1 - 8
  • [42] Data envelopment analysis as method for evaluating intellectual capital
    Leitner, Karl-Heinz
    Schaffhauser-Linzatti, Michaela
    Stowasser, Rainer
    Wagner, Karin
    JOURNAL OF INTELLECTUAL CAPITAL, 2005, 6 (04) : 528 - +
  • [43] Evaluating air quality in China based on daily data: Application of integer data envelopment analysis
    Zhou, Zhixiang
    Guo, Xiumei
    Wu, Huaqing
    Yu, Jie
    JOURNAL OF CLEANER PRODUCTION, 2018, 198 : 304 - 311
  • [44] Evaluating plan quality using data envelopment analysis
    Simpson, J.
    Lin, K. M.
    Raith, A.
    Ehrgott, M.
    Sasso, G.
    RADIOTHERAPY AND ONCOLOGY, 2014, 111 : S155 - S155
  • [45] Optimal Driving Profiles in Railway Systems based on Data Envelopment Analysis
    Achilleos, Achilleas
    Anastasopoulos, Markos
    Tzanakaki, Anna
    Iordache, Marius
    Langlois, Olivier
    Pheulpin, Jean-Francois
    Simeonidou, Dimitra
    PROCEEDINGS OF THE 5TH INTERNATIONAL CONFERENCE ON VEHICLE TECHNOLOGY AND INTELLIGENT TRANSPORT SYSTEMS (VEHITS 2019), 2019, : 254 - 259
  • [46] ACOUSTICAL USER IDENTIFICATION BASED ON MFCC ANALYSIS OF KEYSTROKES
    Pleva, Matus
    Kiktova, Eva
    Juhar, Jozef
    Bours, Patrick
    ADVANCES IN ELECTRICAL AND ELECTRONIC ENGINEERING, 2015, 13 (04) : 316 - 320
  • [48] Evaluating Business Performance of China's Pharmaceutical Companies Based on Data Envelopment Analysis
    Mao, Yunshi
    Li, Jianrui
    Liu, Yangchun
    STUDIES ON ETHNO-MEDICINE, 2014, 8 (01) : 51 - 60
  • [49] An optimal evaluating method for uncertainty metrics in reliability based on uncertain data envelopment analysis
    Zu, Tianpei
    Wen, Meilin
    Kang, Rui
    MICROELECTRONICS RELIABILITY, 2017, 75 : 283 - 287
  • [50] Evaluating the sustainability of Chinese cities: Indicators based on a new data envelopment analysis model
    Liu, Xiaohong
    Liu, Yi
    Wang, Baohui
    ECOLOGICAL INDICATORS, 2022, 137