Skip to Main content Skip to Navigation
Conference papers

I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences

Kong Aik Lee 1 Ville Hautamäki 2 Tomi Kinnunen 2 Hitoshi Yamamoto 1 Koji Okabe 1 Ville Vestman 2, 1 Jing Huang 3 Guohong Ding 4 Hanwu Sun 5 Anthony Larcher 6 Rohan Das 7 Haizhou Li 7 Mickaël Rouvier 8 Pierre-Michel Bousquet 8 Wei Rao 9 Qing Wang 10 Chunlei Zhang 11 Fahimeh Bahmaninezhad 11 Héctor Delgado 12 Jose Patino 12 Qiongqiong Wang 1 Ling Guo 1 Takafumi Koshinaka 1 Jiacen Zhang 1 Koichi Shinoda 1 Trung Ngo Trong 2 Md Sahidullah 13 Fan Lu 4 Yun Tang 4 Ming Tu 4 Kah Kuan Teh 14 Huy Dat Tran 14 Kuruvachan George 14 Ivan Kukanov 14 Florent Desnous 6 Jichen Yang 7 Emre Yılmaz 7 Longting Xu 7 Jean-François Bonastre 8 Chenglin Xu 15 Zhi Lim 15 Siong Chng 15 Shivesh Ranjan 11 John Hansen 11 Massimiliano Todisco 12 Nicholas Evans 12
Abstract : The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE). The latest edition of such joint submission was in SRE 2018, in which the I4U submission was among the best-performing systems. SRE'18 also marks the 10-year anniversary of I4U consortium into NIST SRE series of evaluation. The primary objective of the current paper is to summarize the results and lessons learned based on the twelve subsystems and their fusion submitted to SRE'18. It is also our intention to present a shared view on the advancements, progresses, and major paradigm shifts that we have witnessed as an SRE participant in the past decade from SRE'08 to SRE'18. In this regard, we have seen, among others , a paradigm shift from supervector representation to deep speaker embedding, and a switch of research challenge from channel compensation to domain adaptation.
Document type :
Conference papers
Complete list of metadatas

Cited literature [31 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02280151
Contributor : Anthony Larcher <>
Submitted on : Friday, September 6, 2019 - 9:51:39 AM
Last modification on : Saturday, October 3, 2020 - 3:26:02 AM
Long-term archiving on: : Thursday, February 6, 2020 - 12:10:51 PM

File

i4u_interspeech_2019__arXiv_.p...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02280151, version 1

Citation

Kong Aik Lee, Ville Hautamäki, Tomi Kinnunen, Hitoshi Yamamoto, Koji Okabe, et al.. I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences. INTERSPEECH 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria. ⟨hal-02280151⟩

Share

Metrics

Record views

240

Files downloads

146