"Play PRBLMS": Identifying and Correcting Less Accessible Content in Voice Interfaces
The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
Voice interfaces often struggle with specific types of named content. Domain-specific terminology and naming may push the bounds of standard language, especially in domains like music where artistic creativity extends beyond the music itself. Artists may name themselves with symbols (e.g. M S C RA) that most standard automatic speech recognition (ASR) systems cannot transcribe. Voice interfaces also experience difficulty surfacing content whose titles include non-standard spellings, symbols or other ASCII characters in place of English letters, or are written using a non-standard dialect. We present a generalizable method to detect content that current voice interfaces underserve by leveraging differences in engagement across input modalities. Using this detection method, we develop a typology of content types and linguistic practices that can make content hard to surface. Finally, we present a process using crowdsourced annotations to make underserved content more accessible.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Hill, K. C., & Ladefoged, P. (1977) · Language · doi:10.2307/412918 · Cited by 1,768
Feld, S., & Fox, A. A. (1994) · Annual Review of Anthropology · doi:10.1146/annurev.an.23.100194.000325 · Cited by 375
Gender and Dialect Bias in YouTube’s Automatic Captions
Tatman, R. (2017) · Proceedings of the First ACL Workshop on Ethics in Natural Language Processing · doi:10.18653/v1/w17-1606 · Cited by 338
The microsoft 2016 conversational speech recognition system
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M., Stolcke, A., Yu, D., & Zweig, G. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7953159 · Cited by 326
Real Country: Music and Language in Working-Class Culture
Fox, A. A. (2004) · Project Muse (Johns Hopkins University) · Cited by 301
Real Country: Music and Language in Working-Class Culture
Fox, A. A. (2004) · Duke University Press eBooks · doi:10.1215/9780822385998 · Cited by 300
Demographic dialectal variation in social media: a case study of African-American English
Blodgett, S. L., Green, L., & O'Connor, B. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1120 · Cited by 291
Toward Human Parity in Conversational Speech Recognition
Xiong, W., Droppo, J., Huang, X., Seide, F., Seltzer, M. L., Stolcke, A., Yu, D., & Zweig, G. (2017) · IEEE/ACM Transactions on Audio, Speech, and Language Processing · doi:10.1109/taslp.2017.2756440 · Cited by 245
Accessibility of information on the Web
Lawrence, S., & Giles, C. L. (2000) · intelligence · doi:10.1145/333175.333181 · Cited by 230
Phonological and phonetic characteristics of African American Vernacular English
Thomas, E. R. (2007) · Language and Linguistics Compass · doi:10.1111/j.1749-818x.2007.00029.x · Cited by 217
Drift as a mechanism for cultural change: an example from baby names
Hahn, M. W., & Bentley, R. A. (2003) · Proceedings of the Royal Society of London. Series B: Biological Sciences · doi:10.1098/rsbl.2003.0045 · Cited by 215
Goldwater, S., Jurafsky, D., & Manning, C. D. (2010) · Speech Communication · doi:10.1016/j.specom.2009.10.001 · Cited by 166
Sender-intended functions of emojis in US messaging
Cramer, H., de Juan, P., & Tetreault, J. (2016) · Proceedings of the 18th International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/2935334.2935370 · Cited by 146
Self-citationSearching by Talking: Analysis of Voice Queries on Mobile Web Search
Guy, I. (2016) · Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval · doi:10.1145/2911451.2911525 · Cited by 140 · cited 1×
“However, voice queries are longer and closer to natural language than typed queries [17] and named content can contain naming atypical of speech or long-form text.”
BackgroundMachine transliteration survey
Karimi, S., Scholer, F., & Turpin, A. H. (2011) · ACM Computing Surveys · doi:10.1145/1922649.1922654 · Cited by 133
Comparative study of automatic speech recognition techniques
Cutajar, M., Gatt, E., Grech, I., Casha, O., & Micallef, J. (2013) · IET Signal Processing · doi:10.1049/iet-spr.2012.0151 · Cited by 106
Perea, M., Duñabeitia, J. A., & Carreiras, M. (2008) · Journal of Experimental Psychology: Human Perception and Performance · doi:10.1037/0096-1523.34.1.237 · Cited by 94
Translating unknown queries with web corpora for cross-language information retrieval
Cheng, P., Teng, J., Chen, R.-C., Wang, J., Lu, W., & Chien, L. (2004) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1008992.1009020 · Cited by 93
Data and algorithmic bias in the web
Baeza-Yates, R. (2016) · Proceedings of the 8th ACM Conference on Web Science · doi:10.1145/2908131.2908135 · Cited by 84
Yılmaz, E., van den Heuvel, H., & van Leeuwen, D. A. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.044 · Cited by 80
Auditing Search Engines for Differential Satisfaction Across Demographics
Mehrotra, R., Anderson, A., Diaz, F., Sharma, A., Wallach, H., & Yilmaz, E. (2017) · Proceedings of the 26th International Conference on World Wide Web Companion - WWW '17 Companion · doi:10.1145/3041021.3054197 · Cited by 68
Hip‐Hop Language in Sociolinguistics and Beyond
Cutler, C. (2007) · Language and Linguistics Compass · doi:10.1111/j.1749-818x.2007.00021.x · Cited by 66
Challenges of studying and processing dialects in social media
Jørgensen, A., Hovy, D., & Søgaard, A. (2015) · Proceedings of the Workshop on Noisy User-generated Text · doi:10.18653/v1/w15-4302 · Cited by 62
A comparison and combination of methods for OOV word detection and word confidence scoring
Hazen, T. J., & Bazzi, I. (2002) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2001.940851 · Cited by 52
Effect of pronounciations on OOV queries in spoken term detection
Can, D., Cooper, E., Sethy, A., White, C., Ramabhadran, B., & Saraçlar, M. (2009) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2009.4960494 · Cited by 51
“Don’t Touch My Moustache”: Language Blending and Code Ambiguation by Two J-Pop Artists
Moody, A., & Matsumoto, Y. (2003) · Asian Englishes · doi:10.1080/13488678.2003.10801106 · Cited by 47
A spoken term detection framework for recovering out-of-vocabulary words using the web
Parada, C., Sethy, A., Dredze, M. H., & Jelinek, F. (2010) · Interspeech (USB) · doi:10.21437/interspeech.2010-399 · Cited by 41
Accessibility in information retrieval
Azzopardi, L. A., & Vinay, V. (2008) · Cited by 37
(2011) · Inner Asia · doi:10.1163/000000011799297618 · Cited by 30
Multi-reference WER for evaluating ASR for languages with no orthographic rules
Ali, A. M. A., Magdy, W., Bell, P., & Renals, S. J. (2015) · IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU) · doi:10.1109/asru.2015.7404847 · Cited by 23
Automatic Speech Recognition of English-isiZulu Code-switched Speech from South African Soap Operas
van der Westhuizen, E., & Niesler, T. (2016) · Procedia Computer Science · doi:10.1016/j.procs.2016.04.039 · Cited by 21
Ma, H., Chandrasekar, R., Quirk, C., & Gupta, A. (2009) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/1571941.1572108 · Cited by 18
Bitter Pills to Swallow. ASR and TTS have Drug Problems
Henton, C. G. (2005) · International Journal of Speech Technology · doi:10.1007/s10772-006-5889-0 · Cited by 13
A Multimodal Crowdsourcing Framework for Transcribing Historical Handwritten Documents
Granell, E., & Martínez-Hinarejos, C.-D. (2016) · ACM Symposium on Document Engineering (DocEng) · doi:10.1145/2960811.2960815 · Cited by 13
Pronunciation learning for named-entities through crowd-sourcing
Rutherford, A., Peng, F., & Beaufays, F. (2014) · Interspeech (USB) · doi:10.21437/interspeech.2014-354 · Cited by 11
Laurent, A., Meignier, S., & Deléglise, P. (2014) · Computer Speech & Language · doi:10.1016/j.csl.2014.02.006 · Cited by 10
Situated Dialog in Speech-Based Human-Computer Interaction
Rudnicky, A. I., Raux, A., Lane, I. R., & Misu, T. (2016) · Signals and communication technology · doi:10.1007/978-3-319-21834-2 · Cited by 8
Best, C. T., Shaw, J. A., & Clancy, E. (2013) · Interspeech 2013 · doi:10.21437/interspeech.2013-504 · Cited by 5
Investigating Critical Speech Recognition Errors in Spoken Short Messages
Pappu, A., Misu, T., & Gupta, R. K. (2016) · Signals and communication technology · doi:10.1007/978-3-319-21834-2_7 · Cited by 5
Goto, M., Itou, K., Kitayama, K., & Kobayashi, T. (2004) · Zenodo (CERN European Organization for Nuclear Research) · doi:10.5281/zenodo.1417338 · Cited by 4
Research works printed but not linked: 6
- 10.5555/1793274.1793333 · doi:10.5555/1793274.1793333
- William J. Kountz. 1899. Billy Baxter's Letters. Duquesne Distributing Company.
- Daniel Luzzati Cyril Grouin Ioana Vasilescu Martine Adda-Decker Eric Bilinski Nathalie Camelin Juliette Kahn Carole Lailler Lori Lamel and Sophie Rosset. 2014. Human Annotation of ASR Error Regions: is "gravity" a Sharable Concept for Human Annotators? European Language Resources Association (ELRA). Retrieved from https://hal.archives-ouvertes.fr/hal01134802 · DOI
- 10.5555/1857999.1858024 · doi:10.5555/1857999.1858024
- Attapol T. Rutherford, Fuchun Peng, and Françoise Beaufays. 2014. Pronunciation learning for namedentities through crowd-sourcing. In Fifteenth Annual Conference of the International Speech Communication Association. Retrieved August 11, 2017 from https://mazsola.iit.unimiskolc.hu/~czap/letoltes/IS14/IS2014/PDF/AUTHOR /IS140902.PDF
- State of the U.S. Online Retail Economy in Q1 2017. comScore, Inc. Retrieved September 18, 2017 from http://www.comscore.com/Insights/Presentations-andWhitepapers/2017/State-of-the-US-Online-RetailEconomy-in-Q1--2017
Cited by
Cambre, J., & Kulkarni, C. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359325 · Cited by 119
Springer, A., & Whittaker, S. (2019) · Proceedings of the 24th International Conference on Intelligent User Interfaces · doi:10.1145/3301275.3302322 · Cited by 115
“Major public concerns have arisen following demonstrations of bias in algorithmic systems with regards to gender, race, and other characteristics [9,75,79].”
BackgroundInfluentialSelf-citationVoice as a Design Material: Sociophonetic Inspired Design Strategies in Human-Computer Interaction
Sutton, S. J., Foulkes, P., Kirk, D., & Lawson, S. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300833 · Cited by 92
Progressive Disclosure: When, Why, and How Do Users Want Algorithmic Transparency Information?
Springer, A., & Whittaker, S. (2020) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3374218 · Cited by 84
Self-citationAssessing and addressing algorithmic bias in practice
Cramer, H., Garcia-Gathright, J., Springer, A., & Reddy, S. (2018) · Interactions · doi:10.1145/3278156 · Cited by 52
Self-citation
Metadata
- Authors
- Springer, A., & Cramer, H.
- Affiliations
- University of California, Santa Cruz (US)
- Spotify, San Francisco, CA, USA
- Venue
- Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2018-04-21
- Pages
- 1-13
- OpenAlex
- W2795561066
- Cited by
- 27
- References
- 39
- Citations by year
- 2026: 3 · 2024: 1 · 2021: 2 · 2020: 6 · 2019: 11 · 2018: 4
- FWCI
- 2.35
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- CHI Conference on Human Factors in Computing Systems (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Human Factors and Ergonomics › Digital Accessibility for Disabilities
- Keywords
- speech interfaces, named entity recognition, artist names, non-standard spelling, nonstandard dialects, speech recognition, content accessibility, input modality, engagement, crowdsourced annotation
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.