CoChat

A Survey of Speaker Recognition: Fundamental Theories, Recognition Methods and Opportunities

Open access
Kabir, Muhammad Mohsin, Mridha, M. F., Shin, Jungpil, Jahan, Israt, Ohi, Abu Quwsar · 2021 · IEEE Access
Cited by 128

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Humans can identify a speaker by listening to their voice, over the telephone, or on any digital devices. Acquiring this congenital human competency, authentication technologies based on voice biometrics, such as automatic speaker recognition (ASR), have been introduced. An ASR recognizes speakers by analyzing speech signals and characteristics extracted from speaker's voices. ASR has recently become an effective research area as an essential aspect of voice biometrics. Specifically, this literature survey gives a concise introduction to ASR and provides an overview of the general architectures dealing with speaker recognition technologies, and upholds the past, present, and future research trends in this area. This paper briefly describes all the main aspects of ASR, such as speaker identification, verification, diarization etc. Further, the performance of current speaker recognition systems are investigated in this survey with the limitations and possible ways of improvement. Finally, a few unsolved challenges of speaker recognition are presented at the closure of this survey.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/access.2021.3084299

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Research works printed but not linked: 260

  1. 10.1109/ICASSP.2013.6639171 · doi:10.1109/icassp.2013.6639171
  2. 10.1109/ICASSP.2008.4518619 · DOI
  3. 10.1109/ICASSP.2018.8462628 · DOI · Paper page
  4. 10.1109/ICASSP.2017.7953094 · DOI · Paper page
  5. miguel, 2018, Tied hidden factors in neural networks for end-to-end speaker recognition, arXiv 1812 11946
  6. 10.21437/Interspeech.2018-1545 · DOI · Paper page
  7. 10.21437/Interspeech.2019-2899 · DOI · Paper page
  8. 10.1109/ICASSP.2013.6639063 · DOI
  9. 10.21437/Interspeech.2018-1158 · DOI · Paper page
  10. sarkar, 2011, Eigen-voice based anchor modeling system for speaker identification using MLLR super-vector, Proc 12th Annu Conf Int Speech Commun Assoc, 1
  11. 10.1109/LSP.2012.2221697 · doi:10.1109/lsp.2012.2221697
  12. 10.1109/IE.2013.31 · DOI
  13. 10.1109/ICASSP.2012.6288884 · doi:10.1109/icassp.2012.6288884
  14. trabelsi, 2014, A multi level data fusion approach for speaker identification on telephone speech, arXiv 1407 0380
  15. taghia, 2013, On Von-Mises Fisher mixture model in text-independent speaker identification, Proc INTERSPEECH, 2499, 10.21437/Interspeech.2013-418 · doi:10.21437/interspeech.2013-418
  16. 10.1109/ICASSP.2013.6639065 · doi:10.1109/icassp.2013.6639065
  17. 10.1109/TASE.2015.2467311 · DOI
  18. 10.1109/TASL.2012.2215602 · DOI
  19. prasad, 2013, Multi-frame rate based multiple-model training for robust speaker identification of disguised voice, Proc Int Symp Wireless Personal Multimedia Commun (WPMC), 1
  20. 10.1142/S0218001417500410 · DOI
  21. 10.1145/3195832 · DOI
  22. 10.1016/j.specom.2018.02.009 · DOI
  23. 10.18178/ijmlc.2019.9.1.760 · DOI
  24. sztahó, 2019, Deep learning methods in speaker recognition: A review, arXiv 1911 06615
  25. 10.1109/IRASET48871.2020.9092118 · DOI
  26. 10.5815/ijigsp.2013.09.07 · DOI
  27. manjutha, 2017, Automated speech recognition system—A literature review, Comput Methods Commun Techn Informat, 4, 205
  28. mclaren, 2014, Application of convolutional neural networks to speaker recognition in noisy conditions, Proc 15th Annu Conf Int Speech Commun Assoc, 1
  29. sujiya, 2017, A review on speaker recognition, Int J Eng Technol, 9, 1592, 10.21817/ijet/2017/v9i3/170903513 · DOI
  30. kanagasundaram, 2012, PLDA based speaker recognition on short utterances, IEEE Odyssey Speaker and Language Recognition Workshop, 28
  31. imam, 2017, Speaker recognition using automated systems, AGU International Journal of Engineering & Technology, 5, 31
  32. 10.1109/UPCON.2018.8596954 · doi:10.1109/upcon.2018.8596954
  33. 10.1007/978-3-642-25449-9_21 · doi:10.1007/978-3-642-25449-9_21
  34. 10.1007/978-3-319-07854-0_103 · doi:10.1007/978-3-319-07854-0_103
  35. martin, 1997, The DET curve in assessment of detection task performance, 10.21437/Eurospeech.1997-504 · DOI · Paper page
  36. 10.1109/TASL.2013.2264673 · DOI · Paper page
  37. zhang, 2014, Missing feature reconstruction methods for robust speaker identification, Proc 22nd Eur Signal Process Conf (EUSIPCO), 1482
  38. 10.1186/1687-4722-2014-15 · DOI
  39. 10.1109/ICASSP.2013.6639061 · DOI · Paper page
  40. 10.1109/LSP.2011.2169453 · doi:10.1109/lsp.2011.2169453
  41. qi, 2011, Experiments of GMM based speaker identification, Proc 8th Int Conf Ubiquitous Robots Ambient Intell (URAI), 26
  42. 10.1007/978-3-642-19530-3_10 · doi:10.1007/978-3-642-19530-3_10
  43. 10.1109/ICASSP.2011.5947596 · doi:10.1109/icassp.2011.5947596
  44. 10.1109/TASLP.2014.2308398 · DOI
  45. 10.1007/s10470-017-1069-1 · DOI
  46. 10.1109/FSKD.2012.6233866 · doi:10.1109/fskd.2012.6233866
  47. 10.1016/j.bspc.2018.09.003 · DOI
  48. 10.1016/j.specom.2009.08.009 · DOI · Paper page
  49. 10.1109/MCAS.2011.941079 · DOI · Paper page
  50. 10.1007/978-3-642-17641-8_18 · DOI
  51. 10.1145/3015166.3015210 · DOI
  52. 10.1109/ICASSP.2019.8683892 · DOI · Paper page
  53. 10.1080/02564602.2016.1185976 · DOI
  54. 10.1109/SLT.2014.7078610 · DOI · Paper page
  55. 10.1016/j.eswa.2017.08.015 · DOI · Paper page
  56. fisher, 1986, Ther DARPA speech recognition research database: Specifications and status, Proc DARPA Workshop Speech Recognit, 93
  57. 10.1109/TIFS.2011.2166387 · doi:10.1109/tifs.2011.2166387
  58. 10.1109/TASL.2010.2091631 · DOI
  59. 10.1007/978-3-642-28931-6_46 · DOI
  60. 10.1007/978-3-319-23132-7_48 · DOI
  61. 10.1504/IJBM.2013.055972 · doi:10.1504/ijbm.2013.055972
  62. 10.5220/0005191701780185 · doi:10.5220/0005191701780185
  63. 10.1109/FSKD.2012.6234345 · DOI
  64. 10.1007/978-3-319-39627-9_41 · doi:10.1007/978-3-319-39627-9_41
  65. 10.1515/bams-2014-0006 · doi:10.1515/bams-2014-0006
  66. 10.1016/j.specom.2011.01.007 · DOI
  67. 10.1515/jisys-2012-0050 · doi:10.1515/jisys-2012-0050
  68. saeidi, 2012, Exemplar-based sparse representation and sparse discrimination for noise robust speaker identification, IEEE Odyssey Speaker and Language Recognition Workshop, 1
  69. 10.21437/Interspeech.2019-2441 · DOI · Paper page
  70. can kocabiyikoglu, 2018, Augmenting librispeech with French translations: A multimodal corpus for direct speech translation evaluation, arXiv 1802 03142
  71. wildermoth, 2003, GMM based speaker recognition on readily available databases, Proc Microelectron Eng Res Conf, 7, 55
  72. 10.1016/j.dsp.2014.06.007 · DOI
  73. 10.1016/j.compeleceng.2012.05.011 · DOI
  74. 10.1016/j.specom.2013.09.004 · doi:10.1016/j.specom.2013.09.004
  75. 10.1109/TASLP.2014.2355821 · DOI
  76. 10.1145/2975161 · doi:10.1145/2975161
  77. 10.1142/S0218001414560060 · DOI
  78. 10.1186/1687-4722-2014-13 · DOI
  79. mitra, 2013, Modulation features for noise robust speaker identification, Proc INTERSPEECH, 3703, 10.21437/Interspeech.2013-695 · doi:10.21437/interspeech.2013-695
  80. michalevsky, 2011, Speaker identification using diffusion maps, Proc 19th Eur Signal Process Conf, 1299
  81. 10.1109/ICASSP.2012.6288853 · doi:10.1109/icassp.2012.6288853
  82. 10.1109/TASL.2010.2101594 · DOI
  83. 10.1007/978-3-642-39593-2_13 · doi:10.1007/978-3-642-39593-2_13
  84. hanilçi, 2013, Speaker identification from shouted speech: Analysis and compensation, Proc IEEE Int Conf Acoust Speech Signal Process, 8027
  85. 10.4103/0256-4602.50702 · DOI
  86. shaver, 2016, A brief review of speaker recognition technology
  87. hasan, 2004, Speaker identification using MEL frequency cepstral coefficients, Variations, 1, 1
  88. 10.5120/8529-2061 · doi:10.5120/8529-2061
  89. 10.1007/978-3-540-49127-9_37 · DOI
  90. 10.4304/jmm.9.4.553-561 · doi:10.4304/jmm.9.4.553-561
  91. 10.1002/j.1538-7305.1987.tb00198.x · DOI
  92. 10.1109/CCECE.2011.6030515 · doi:10.1109/ccece.2011.6030515
  93. stafylakis, 2013, Text-dependent speaker recognition using PLDA with uncertainty propagation, Matrix, 500, 1
  94. 10.1109/ICASSP.2011.5947465 · DOI
  95. 10.1007/978-3-642-01793-3_106 · doi:10.1007/978-3-642-01793-3_106
  96. 10.1109/ICASSP.2011.5947590 · DOI · Paper page
  97. 10.1109/MWSCAS.2001.986114 · doi:10.1109/mwscas.2001.986114
  98. dhonde, 2015, Feature extraction techniques in speaker recognition: A review, Recent Technol Mech Electr Eng, 2, 104
  99. desai, 2016, Speaker recognition system using watermark technology for anti-spoofing attack: A review, Int J Innov Res Electr Electron Instrum Control Eng, 4, 152
  100. sharma, 2013, A review on speaker recognition approaches and challenges, Int J Eng Res Technol, 2, 1581
  101. 10.1109/APSIPA.2014.7041826 · DOI
  102. 10.1109/ICASSP.2018.8461423 · DOI
  103. 10.1109/TASLP.2018.2831456 · DOI · Paper page
  104. 10.21437/Interspeech.2017-49 · DOI
  105. 10.1109/ICACCI.2015.7275749 · doi:10.1109/icacci.2015.7275749
  106. 10.1016/j.specom.2011.11.004 · DOI · Paper page
  107. 10.1007/11821045_19 · doi:10.1007/11821045_19
  108. 10.1016/j.procs.2010.11.022 · doi:10.1016/j.procs.2010.11.022
  109. 10.1109/ICASSP.2003.1198793 · DOI · Paper page
  110. 10.1109/ODYSSEY.2006.248083 · doi:10.1109/odyssey.2006.248083
  111. 10.1109/ICASSP.2018.8461690 · DOI
  112. 10.1145/958432.958485 · doi:10.1145/958432.958485
  113. 10.1007/978-3-642-32639-4_55 · doi:10.1007/978-3-642-32639-4_55
  114. 10.1109/SPED.2015.7343091 · DOI
  115. nunes, 2020, AM-MobileNet1D: A portable model for speaker recognition, Proc Int Joint Conf Neural Netw (IJCNN), 1
  116. 10.1109/SLT.2014.7078604 · DOI
  117. 10.21437/Odyssey.2016-25 · DOI
  118. 10.1007/s13735-014-0055-y · doi:10.1007/s13735-014-0055-y
  119. mosa, 2009, Arabic phoneme recognition using hierarchical neural fuzzy Petri net and LPC feature extraction, Signal Process Int J, 3, 161
  120. yousefian, 2007, Using radial basis probabilistic neural network for speech recognition, Proc 3rd Int Conf Inf Knowl (IKT), 1
  121. 10.1007/978-3-319-12012-6_58 · doi:10.1007/978-3-319-12012-6_58
  122. 10.1109/ICASSP.2011.5947588 · doi:10.1109/icassp.2011.5947588
  123. 10.1109/ICASSP.2011.5947591 · doi:10.1109/icassp.2011.5947591
  124. 10.1007/978-3-642-27387-2_44 · doi:10.1007/978-3-642-27387-2_44
  125. 10.1016/j.csl.2019.101026 · DOI
  126. 10.1109/ICASSP.2019.8683760 · DOI · Paper page
  127. 10.1016/j.pmcj.2011.02.005 · doi:10.1016/j.pmcj.2011.02.005
  128. 10.21437/Interspeech.2016-1144 · doi:10.21437/interspeech.2016-1144
  129. 10.1109/ICSMC.2011.6083903 · DOI
  130. 10.21437/Interspeech.2016-1129 · DOI · Paper page
  131. 10.1145/2708463.2709049 · doi:10.1145/2708463.2709049
  132. 10.21437/Interspeech.2016-1465 · doi:10.21437/interspeech.2016-1465
  133. 10.21437/Interspeech.2016-1174 · doi:10.21437/interspeech.2016-1174
  134. 10.1007/s10772-016-9385-x · doi:10.1007/s10772-016-9385-x
  135. 10.1109/CONIELECOMP.2012.6189918 · DOI
  136. 10.1109/ICASSP.2018.8461375 · DOI · Paper page
  137. feng, 2005, A New Database for Speaker Recognition
  138. drygajlo, 2003, Statistical methods and Bayesian interpretation of evidence in forensic automatic speaker recognition, Proc 8th Eur Conf Speech Commun Technol, 1
  139. 10.1109/ICASSP.2012.6288986 · DOI
  140. alam, 2014, Supervised/unsupervised voice activity detectors for text-dependent speaker recognition on the RSR2015 corpus, IEEE Odyssey Speaker and Language Recognition Workshop, 123
  141. 10.1145/3209978.3209997 · DOI
  142. 10.21437/Interspeech.2016-1125 · DOI
  143. 10.21437/Interspeech.2016-929 · DOI
  144. 10.1109/ICASSP.1994.389346 · DOI
  145. nguyen, 2010, Automatic classification of speaker characteristics, Proc Int Conf Commun Electron, 147
  146. logan, 2000, Mel frequency cepstral coefficients for music modeling, Proc ISMIR, 270, 1
  147. 10.1007/s00521-012-0946-x · doi:10.1007/s00521-012-0946-x
  148. 10.3390/make1010031 · DOI
  149. agrawal, 2010, Prosodic feature based text dependent speaker recognition using machine learning algorithms, Int J Eng Sci Technol, 2, 5150
  150. 10.1121/1.399423 · DOI · Paper page
  151. narang, 2015, Speech feature extraction techniques: A review, Int J Comput Sci Mobile Comput, 4, 107
  152. 10.1109/MSP.2006.1598091 · DOI
  153. 10.1007/s10916-010-9591-z · doi:10.1007/s10916-010-9591-z
  154. kumar, 2011, Speaker identification using Gaussian mixture models, MIT International Journal of Electronics and Communication Engineering, 1, 27
  155. kumar, 2009, Multilingual speaker recognition using neural network, Proc Frontiers Res Speech Music (FRSM), 1
  156. rao, 2011, Recognition and a panoramic view of Raaga emotions of singers-application Gaussian mixture model, International Journal of Research and Reviews in Computer Science, 2, 201
  157. 10.1109/ICASSP.2008.4517531 · doi:10.1109/icassp.2008.4517531
  158. paulraj, 2009, A speech recognition system for Malaysian English pronunciation using neural network, Pro Int Conf Man-Mach Syst
  159. al-sarayreh, 2009, Using the sound recognition techniques to reduce the electricity consumption in highways, J Amer Sci, 5, 1
  160. el choubassi, 2003, Arabic speech recognition using recurrent neural networks, Proc 3rd IEEE Int Symp Signal Process Inf Technol, 543
  161. wu, 1997, On-line signature verification using LPC cepstrum and neural networks, IEEE Trans Syst Man Cybern B Cybern, 27, 148, 10.1109/3477.552197 · doi:10.1109/3477.552197
  162. 10.1109/ISCIT.2004.1412458 · DOI
  163. 10.1007/978-0-387-73003-5_196 · DOI · Paper page
  164. kumar, 2010, Speaker recognition using GMM, Int J Eng Sci Technol, 2, 2428
  165. 10.21437/Interspeech.2017-620 · DOI · Paper page
  166. 10.1109/SLT.2016.7846260 · DOI · Paper page
  167. 10.1109/ICASSP.2019.8683097 · DOI
  168. 10.1109/TASLP.2014.2352154 · DOI
  169. jin, 2000, Application of LDA to speaker recognition, Proc Int Conf Spoken Lang Process, 1
  170. amodei, 2016, Deep speech 2: End-to-end speech recognition in English and Mandarin, Proc Int Conf Mach Learn, 173
  171. 10.21437/Interspeech.2017-452 · DOI
  172. 10.1145/967900.968151 · doi:10.1145/967900.968151
  173. 10.1016/0146-664X(80)90054-4 · DOI · Paper page
  174. novoselov, 2014, STC speaker recognition system for the NIST i-vector challenge, Proc Odyssey, 231, 10.21437/Odyssey.2014-35 · DOI
  175. khosravani, 2014, Linearly constrained minimum variance for robust i-vector based speaker recognition, Proc Odyssey, 1
  176. zhang, 2020, Speaker verification system based on deformable CNN and time-frequency attention, Proc Asia–Pacific Signal Inf Process Assoc Annu Summit Conf (APSIPA ASC), 1689
  177. 10.1109/ICASSP40776.2020.9054423 · DOI
  178. 10.1007/978-3-030-63823-8_10 · doi:10.1007/978-3-030-63823-8_10
  179. 10.21437/Interspeech.2020-1064 · DOI · Paper page
  180. zeinali, 2019, BUT system description to VoxCeleb speaker recognition challenge 2019, arXiv 1910 12592
  181. hajibabaei, 2018, Unified hypersphere embedding for speaker recognition, arXiv 1807 08312
  182. carletta, 2005, The ami meeting corpus: A pre-announcement, Proc Int Workshop Mach Learn Multimodal Interact, 28
  183. kanagasundaram, 2011, I-vector based speaker recognition on short utterances, Proc 12th Annu Conf Int Speech Commun Assoc, 2341
  184. 10.21437/Odyssey.2018-11 · DOI · Paper page
  185. 10.1109/APSIPA.2017.8282083 · DOI
  186. yaman, 2012, Bottleneck features for speaker recognition, IEEE Odyssey Speaker and Language Recognition Workshop, 1
  187. 10.1016/j.phpro.2012.03.270 · doi:10.1016/j.phpro.2012.03.270
  188. 10.1109/LSP.2015.2420092 · DOI · Paper page
  189. 10.1109/ASRU.2013.6707705 · DOI · Paper page
  190. 10.1109/ISCSLP.2012.6423485 · doi:10.1109/iscslp.2012.6423485
  191. 10.1109/ASRU.2015.7404863 · DOI
  192. 10.1007/978-3-319-10816-2_46 · doi:10.1007/978-3-319-10816-2_46
  193. 10.1109/ICASSP.2012.6288889 · doi:10.1109/icassp.2012.6288889
  194. 10.1007/978-3-642-21726-5_12 · DOI
  195. 10.1007/978-3-642-34135-9_13 · doi:10.1007/978-3-642-34135-9_13
  196. 10.1109/ICASSP.2013.6638972 · DOI
  197. 10.1109/ICASSP.2015.7178775 · doi:10.1109/icassp.2015.7178775
  198. 10.1016/j.eswa.2010.11.013 · DOI
  199. singh, 2014, A study on speech and speaker recognition technology and its challenges, Proc Nat Conf Inf Secur Challenges, 34
  200. 10.1109/ICASSP.2012.6288886 · doi:10.1109/icassp.2012.6288886

200 of 260 shown

Cited by

See all 128

Metadata

Authors
Kabir, M. M., Mridha, M. F., Shin, J., Jahan, I., & Ohi, A. Q.
Venue
IEEE Access
Published
2021
Volume
9
Pages
79236-79263
ISSN
2169-3536 (ISSN-L)
OpenAlex
W3171302872
Cited by
128
References
14
FWCI
7.85
Type
journal article
Language
en
Open access
gold

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.