Skip to main content
U.S. flag

An official website of the United States government

Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

OpenASR20 Challenge Results

The OpenASR (Open Automatic Speech Recognition) 2020 Challenge was the second open challenge associated with the IARPA MATERIAL program, after the OpenCLIR (Open Cross-Language Information Retrieval) 2019 Challenge. Capabilities tested in these open challenges are expected to ultimately support the MATERIAL task of effective triage and analysis of large volumes of text and audio content in a variety of less-studied languages. OpenASR20 was implemented as a track of NIST’s OpenSAT (Speech Analytic Technologies) evaluation series.

The goal of the OpenASR20 challenge was to assess the state of the art of automatic speech recognition (ASR) technologies for low-resource languages. ASR was performed on speech datasets, and written text output had to be produced.

Please refer to the OpenASR20 Challenge Evaluation Plan for a full description of the challenge and its rules and procedures.

Languages

OpenASR20 was offered for the following ten low-resource languages, of which participants could attempt as many as they wished:

  • Amharic (AMH)
  • Cantonese (CAN)
  • Guarani (GUA)
  • Javanese (JAV)
  • Kurmanji Kurdish (KUR)
  • Mongolian (MON)
  • Pashto (PAS)
  • Somali (SOM)
  • Tamil (TAM)
  • Vietnamese (VIE)

Data

The data for the challenge consisted of conversational telephone speech stemming from the IARPA Babel program, with the exception of Somali which stemmed from MATERIAL. More details regarding technical data details can be found in section 3 of the IARPA Babel Data Specifications for PerformersFor each language, separate training, development, and evaluation datasets were provided.

Training Conditions

The challenge offered two training conditions: 

  • Constrained training (mandatory):
    • Speech data: Limited to a 10-hour subset designated for Constrained training in provided training dataset for the language in question
    • Non-speech data: Any publicly available data
  • Unconstrained training (optional): Any publicly available data

Metrics

  • Primary metric: Word Error Rate (WER)
  • Additional metrics:
    • Character Error Rate (CER)
    • Time and memory resources used (self-reported)

Schedule

The most important milestones of the schedule of the challenge were as follows:

  • Registration: August - October, 2020
  • Development period: August 2020 - June 15, 2021
  • Evaluation period: November 3-10, 2020

Participation

28 teams from 12 countries registered to participate, out of which nine fully completed the challenge (i.e. submitted valid output for at least one language under the Constrained training condition). Table 1 lists the fully participating teams.

 

OrganizationTeam

AMH

CAN

GUA

JAV

KUR

MON

PAS

SOM

TAM

VIE

Catskills Research Co., USACatskills       

x

  
Centre de Recherche Informatique de Montréal, CanadaCRIM    

x

     
Tencent, ChinaMMT     

x

    
National Sun Yat-sen University, TaiwanNSYSU-MITLab 

x

       

x

Speechlab, Shanghai Jiao Tong University, ChinaSpeechlab_SJTU

x

x

x

x

x

x

 

x

x

 
Tallinn University of Technology, EstoniaTalTech

x

x

x

x

x

x

x

x

x

x

Tsinghua University, ChinaTHUEE

x

x

x

x

x

x

x

x

x

x

Tencent & Tsinghua University, ChinaTNT 

x

   

x

    
Tal, Chinaupteam

x

x

x

x

x

x

x

x

x

x

Table 1: OpenASR20 Participants

Results

Table 2 lists the best WER result achieved by each team, ordered by language, training condition (Unconstrained submissions in italics), and WER score. Late submissions are marked as such and listed at the bottom of the table. Self-reported time and memory resources are not included in this overview of results.

On-time Submissions
LanguageTraining ConditionTeamWERCER
AmharicConstrainedTalTech0.45050.3430
AmharicConstrainedTHUEE0.45820.3528
AmharicConstrainedSpeechlab_SJTU1.01620.8897
AmharicConstrainedupteam1.38411.3621
AmharicUnconstrainedSpeechlab_SJTU1.01620.8897
LanguageTraining ConditionTeamWERCER
CantoneseConstrainedTNT0.40240.3511
CantoneseConstrainedTHUEE0.43620.3798
CantoneseConstrainedTalTech0.45400.4005
CantoneseConstrainedNSYSU-MITLab0.61450.5588
CantoneseConstrainedSpeechlab_SJTU0.75860.7040
CantoneseConstrainedupteam1.31331.3301
CantoneseUnconstrainedTNT0.32000.2643
CantoneseUnconstrainedSpeechlab_SJTU0.75860.7040
LanguageTraining ConditionTeamWERCER
GuaraniConstrainedTHUEE0.46090.4216
GuaraniConstrainedTalTech0.46640.4314
GuaraniConstrainedSpeechlab_SJTU0.99090.9611
GuaraniConstrainedupteam1.21431.2127
GuaraniUnconstrainedSpeechlab_SJTU0.99090.9611
LanguageTraining ConditionTeamWERCER
JavaneseConstrainedTHUEE0.52100.5216
JavaneseConstrainedTalTech0.53760.5384
JavaneseConstrainedSpeechlab_SJTU0.94430.9447
JavaneseConstrainedupteam1.34901.3490
JavaneseUnconstrainedSpeechlab_SJTU0.94430.9447
LanguageTraining ConditionTeamWERCER
Kurmanji-KurdishConstrainedTalTech0.65290.6107
Kurmanji-KurdishConstrainedTHUEE0.66860.6236
Kurmanji-KurdishConstrainedCRIM0.75290.7091
Kurmanji-KurdishConstrainedupteam1.09051.0810
Kurmanji-KurdishConstrainedSpeechlab_SJTU1.11981.0500
Kurmanji-KurdishUnconstrainedSpeechlab_SJTU1.11981.0500
LanguageTraining ConditionTeamWERCER
MongolianConstrainedTHUEE0.45400.3297
MongolianConstrainedMMT0.45460.3310
MongolianConstrainedTalTech0.47290.3452
MongolianConstrainedSpeechlab_SJTU0.97170.8045
MongolianConstrainedupteam1.02891.0042
MongolianUnconstrainedMMT0.40640.2998
MongolianUnconstrainedTNT0.45540.3369
MongolianUnconstrainedSpeechlab_SJTU0.97170.8045
LanguageTraining ConditionTeamWERCER
PashtoConstrainedTalTech0.45680.3163
PashtoConstrainedTHUEE0.48590.3391
PashtoConstrainedupteam1.37321.3488
LanguageTraining ConditionTeamWERCER
SomaliConstrainedTalTech0.59140.5926
SomaliConstrainedTHUEE0.59580.5967
SomaliConstrainedSpeechlab_SJTU1.04441.0449
SomaliConstrainedCatskills1.13851.1390
SomaliConstrainedupteam1.23011.2301
SomaliUnconstrainedSpeechlab_SJTU1.04441.0449
LanguageTraining ConditionTeamWERCER
TamilConstrainedTalTech0.65110.4165
TamilConstrainedTHUEE0.66050.4426
TamilConstrainedSpeechlab_SJTU1.05550.8027
TamilConstrainedupteam1.35131.3207
TamilUnconstrainedSpeechlab_SJTU1.05550.8027
LanguageTraining ConditionTeamWERCER
VietnameseConstrainedTalTech0.45140.4069
VietnameseConstrainedTHUEE0.46050.4125
VietnameseConstrainedNSYSU-MITLab0.74610.7023
VietnameseConstrainedupteam1.41071.4121
Late Submissions
LanguageTraining ConditionTeamWERCER
MongolianConstrainedTNT†0.4500†0.3515†

Table 2: OpenASR20 Results. † = late submission.

System Descriptions

As part of the evaluation submission, participants were required to include a paper to describe their systems. Participants were also encouraged to submit their work to be included in the OpenASR and Low-Resource ASR Development Special Session at INTERSPEECH 2021. The system descriptions with consent to be released publicly are provided below:

Disclaimer

NIST serves to coordinate the evaluations in order to support research and to help advance the state- of-the-art. NIST evaluations are not viewed as a competition, and such results reported by NIST are not to be construed, or represented, as endorsements of any participant’s system, or as official findings on the part of NIST or the U.S. Government.

Contact

Please email openasr_poc [at] nist.gov (openasr_poc[at]nist[dot]gov) for any questions or comments regarding the OpenASR Challenge.

Created January 12, 2021, Updated April 30, 2025