Automatic Speech Recognition for Supporting Endangered Language Documentation

被引:0
作者
Prud'hommeaux, Emily [1 ]
Jimerson, Robbie [2 ]
Hatcher, Richard [3 ]
Michelson, Karin [3 ]
机构
[1] Boston Coll, Chestnut Hill, MA 02167 USA
[2] Rochester Inst Technol, Rochester, NY USA
[3] Univ Buffalo, Buffalo, NY USA
来源
LANGUAGE DOCUMENTATION & CONSERVATION | 2021年 / 15卷
基金
美国国家科学基金会;
关键词
UNDER-RESOURCED LANGUAGES; NEURAL-NETWORKS; TRANSCRIPTION; ALIGNMENT; ASR;
D O I
暂无
中图分类号
H0 [语言学];
学科分类号
030303 ; 0501 ; 050102 ;
摘要
Generating accurate word-level transcripts of recorded speech for language documentation is difficult and time-consuming, even for skilled speakers of the target language. Automatic speech recognition (ASR) has the potential to streamline transcription efforts for endangered language documentation, but the practical utility of ASR for this purpose has not been fully explored. In this paper, we present results of a study in which both linguists and community members, with varying levels of language proficiency, transcribe audio recordings of an endangered language under timed conditions with and without the assistance of ASR. We find that both time-to-transcribe and transcription error rates are significantly reduced when correcting ASR for language learners of all levels. Despite these improvements, most community members in our study express a preference for unassisted transcription, highlighting the need for developers to directly engage with stakeholders when designing and deploying technologies for supporting language documentation.
引用
收藏
页码:491 / 513
页数:23
相关论文
共 78 条
[21]  
Chafe Wallace., 2014, GRAMMAR SENECA LANGU, V149
[22]  
Coto-Solano R., 2017, CLEI ELECT J, V20, P2
[23]  
Czaykowska-Higgins E, 2009, LANG DOC CONSERV, V3, P15
[24]   Listening to what is said - transcribing what is heard: the impact of speech recognition technology (SRT) on the practice of medical transcription (MT) [J].
David, Gary C. ;
Garcia, Angela Cora ;
Rawls, Anne Warfield ;
Chand, Donald .
SOCIOLOGY OF HEALTH & ILLNESS, 2009, 31 (06) :924-938
[25]   Using automatic alignment to analyze endangered language data: Testing the viability of untrained alignment [J].
DiCanio, Christian ;
Nam, Hosung ;
Whalen, Douglas H. ;
Bunnell, H. Timothy ;
Amith, Jonathan D. ;
Castillo Garcia, Rey .
JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2013, 134 (03) :2235-2246
[26]  
DiCanio CT, 2012, 13TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2012 (INTERSPEECH 2012), VOLS 1-3, P130
[27]  
Eberhard DM., 2021, ETHNOLOGUE LANGUAGES, DOI DOI 10.4324/9781315229140
[28]  
Foley Ben., 2018, Proceedings of The 6th International Workshop on Spoken Language Technologies for Under-Resourced Languages, P205
[29]  
Gauthier E, 2016, LREC 2016 - TENTH INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, P3863
[30]  
Gelas Hadrien, 2012, SLTUWORKSHOP SPOKEN, P94