I-vector-based Speaker Identification with Extremely Short Utterances for Both Training and Testing

被引：0
|
作者：
Tsujikawa, Misaki [1 ]
Nishikawa, Tsuyoki [1 ]
Matsui, Tomoko [2 ]
机构：
[1] Panasonic Corp, Core Technol Elemental Dev Ctr, Kadoma, Osaka, Japan
[2] Inst Stat Math, Tachikawa, Tokyo, Japan
来源：
2017 IEEE 6TH GLOBAL CONFERENCE ON CONSUMER ELECTRONICS (GCCE) | 2017年
关键词：
Speaker identification; i-vector; Extremely short utterances;
D O I：
暂无
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
Voice applications often require the ability to make user-friendly responses by judging the user or user-type from an extremely short utterance, such as a single word. However, it is assumed that performance becomes degraded as the utterance length decreases. In this paper, we examine the performance of speaker identification for extremely short utterances of less than two seconds and then study the relationship between the accuracy and utterance length. Moreover, we show that the identification accuracy can be improved by selecting similar speakers to the target user from a large speech corpus.
引用
收藏
页数：4
相关论文
共 50 条
  • [1] Integration of MKL-based and i-vector-based speaker verification by short
    Hino, Hideitsu
    Ogawa, Tetsuji
    2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013), 2013, : 562 - 566
  • [2] i-vector Based Speaker Recognition on Short Utterances
    Kanagasundaram, Ahilan
    Vogt, Robbie
    Dean, David
    Sridharan, Sridha
    Mason, Michael
    12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 2352 - +
  • [3] GMM and i-vector based speaker verification using speaker-specific-text for short utterances
    Bharathi, B.
    Nagarajan, T.
    2013 IEEE INTERNATIONAL CONFERENCE OF IEEE REGION 10 (TENCON), 2013,
  • [4] Improved i-vector extraction technique for speaker verification with short utterances
    Poddar A.
    Sahidullah M.
    Saha G.
    International Journal of Speech Technology, 2018, 21 (03) : 473 - 488
  • [5] A Study of X-vector Based Speaker Recognition on Short Utterances
    Kanagasundaram, A.
    Sridharan, S.
    Sriram, G.
    Prachi, S.
    Fookes, C.
    INTERSPEECH 2019, 2019, : 2943 - 2947
  • [6] i-Vector-Based Speaker Verification on Limited Data Using Fusion Techniques
    Kumari, T. R. Jayanthi
    Jayanna, H. S.
    JOURNAL OF INTELLIGENT SYSTEMS, 2020, 29 (01) : 565 - 582
  • [7] Deep neural network based i-vector mapping for speaker verification using short utterances
    Guo, Jinxi
    Xu, Ning
    Qian, Kailun
    Shi, Yang
    Xu, Kaiyuan
    Wu, Yingnian
    Alwan, Abeer
    SPEECH COMMUNICATION, 2018, 105 : 92 - 102
  • [8] X-vectors based Urdu Speaker Identification for short utterances
    Farooq, Muhammad Umar
    Adeeba, Farah
    Hussain, Sarmad
    2019 22ND CONFERENCE OF THE ORIENTAL COCOSDA INTERNATIONAL COMMITTEE FOR THE CO-ORDINATION AND STANDARDISATION OF SPEECH DATABASES AND ASSESSMENT TECHNIQUES (O-COCOSDA), 2019, : 19 - 23
  • [9] A COMPARATIVE STUDY OF SPECTRAL CLUSTERING FOR I-VECTOR-BASED SPEAKER CLUSTERING UNDER NOISY CONDITIONS
    Tawara, Naohiro
    Ogawa, Tetsuji
    Kobayashi, Tetsunori
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 2041 - 2045
  • [10] I-VECTOR-BASED SPEAKER ADAPTATION OF DEEP NEURAL NETWORKS FOR FRENCH BROADCAST AUDIO TRANSCRIPTION
    Gupta, Vishwa
    Kenny, Patrick
    Ouellet, Pierre
    Stafylakis, Themos
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2014,
12345