Underlying Text Independent Speaker Recognition

被引:0
|
作者
Singh, Nilu [1 ]
Khan, R. A. [1 ]
机构
[1] Babasaheb Bhimrao Ambedkar Univ, SIST DIT, Lucknow, Uttar Pradesh, India
关键词
Automatic Speaker Recognition; Identification; Verification; High-Level Features; Technical Challenges; Evaluation Factors for Performance of Speaker Recognition;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper discusses the evaluation of automatic speaker recognition from numerous perspectives. A general discussion of the Speaker recognition task, challenges and issues involved in its evaluation is discussed. Speaker recognition have many factors that found to have an impact on performance of recognition rate such as pitch, frequency, handset type and hack ground noise etc. We start with the fundamentals of automatic speaker recognition, features type concerning feature extraction technique and speaker modeling. Automatic Speaker Recognition is the procedure to automatically recognizing a person based on their speech waves including speaker specific information. It is a procedure to identification and verification of a speaker. Speaker Recognition supports access control for different voice based services such as voice dialing, voice mail, telephone shopping, database access services, banking services by telephone, information and reservation services, security control for confidential information, remote access to computers and the another important application of speaker recognition technology is in forensics.
引用
收藏
页码:6 / 10
页数:5
相关论文
共 50 条
  • [21] Text-independent speaker recognition using graph matching
    Hautamaki, Ville
    Kinnunen, Tomi
    Franti, Pasi
    PATTERN RECOGNITION LETTERS, 2008, 29 (09) : 1427 - 1432
  • [22] A discriminative training approach for text-independent speaker recognition
    Hong, QY
    Kwong, S
    SIGNAL PROCESSING, 2005, 85 (07) : 1449 - 1463
  • [23] Compensation for domain mismatch in text-independent speaker recognition
    Bahmaninezhad, Fahimeh
    Hansen, John H. L.
    19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 1071 - 1075
  • [24] I-MATRIX FOR TEXT-INDEPENDENT SPEAKER RECOGNITION
    He, Liang
    Liu, Jia
    2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 7194 - 7198
  • [25] Investigation of the effect of data duration and speaker gender on text-independent speaker recognition
    Hanilci, Cemal
    Ertas, Figen
    COMPUTERS & ELECTRICAL ENGINEERING, 2013, 39 (02) : 441 - 452
  • [26] Source and System Features for Text Independent Speaker Recognition Using GMM Speaker Models
    Revathi, A.
    Venkataramani, Y.
    RECENT TRENDS IN NETWORKS AND COMMUNICATIONS, 2010, 90 : 21 - +
  • [27] VQ score normalisation for text-dependent and text-independent speaker recognition
    Finan, RA
    Sapeluk, AT
    Damper, RI
    AUDIO- AND VIDEO-BASED BIOMETRIC PERSON AUTHENTICATION, 1997, 1206 : 211 - 218
  • [28] A Multiscale Feature Extraction Method for Text-independent Speaker Recognition
    Chen Zhigao
    Li Peng
    Xiao Runqiu
    Li Ta
    Wang Wenchao
    JOURNAL OF ELECTRONICS & INFORMATION TECHNOLOGY, 2021, 43 (11) : 3266 - 3271
  • [29] Cepstral Trajectories in Linguistic Units for Text-Independent Speaker Recognition
    Franco-Pedroso, Javier
    Espinoza-Cuadros, Fernando
    Gonzalez-Rodriguez, Joaquin
    ADVANCES IN SPEECH AND LANGUAGE TECHNOLOGIES FOR IBERIAN LANGUAGES, 2012, 328 : 20 - 29
  • [30] Deep Speaker Embeddings with Convolutional Neural Network on Supervector for Text-Independent Speaker Recognition
    Cai, Danwei
    Cai, Zexin
    Li, Ming
    2018 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA ASC), 2018, : 1478 - 1482