Choice of Voices: A Large-Scale Evaluation of Text-to-Speech Voice Quality for Long-Form Content
Open accessThe DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
The advancement of text-to-speech (TTS) voices and a rise of commercial TTS platforms allow people to easily experience TTS voices across a variety of technologies, applications, and form factors. As such, we evaluated TTS voices for long-form content: not individual words or sentences, but voices that are pleasant to listen to for several minutes at a time. We introduce a method using a crowdsourcing platform and an online survey to evaluate voices based on listening experience, perception of clarity and quality, and comprehension. We evaluated 18 TTS voices, three human voices, and a text-only control condition. We found that TTS voices are close to rivaling human voices, yet no single voice outperforms the others across all evaluation dimensions. We conclude with considerations for selecting text-to-speech voices for long-form content.
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.
Integrity signals
Registry
Cites
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.
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
Luger, E., & Sellen, A. (2016) · Proceedings of the 2016 CHI Conference on Human Factors in Computing Systems · doi:10.1145/2858036.2858288 · Cited by 1,176 · cited 1×
“In studies of users’ experiences with today’s common voice assistants, researchers found that the human-like names, personalities, and voices the assistants take on mislead users into expecting human-like intelligence [14, 31].”
BackgroundAre Machines Gender Neutral? Gender‐Stereotypic Responses to Computers With Voices
Nass, C., Moon, Y., & Green, N. (1997) · Journal of Applied Social Psychology · doi:10.1111/j.1559-1816.1997.tb00275.x · Cited by 670 · cited 2×
“…voice features such as gender and accent (see [36] and [11] for a review), suggesting, for example, that voices may activate gender stereotypes [32, 38, 48] and influence the perceived credibility of a voice-based agent [1, 16], and that these perceptions may change depending on how human-like a…”
BackgroundResultNass, C., & Lee, K. M. (2001) · Journal of Experimental Psychology: Applied · doi:10.1037/1076-898x.7.3.171 · Cited by 522 · cited 2×
“In one study, researchers created introvert and extrovert versions of a TTS voice by manipulating parameters like the voice’s volume, speaking rate, and frequency range [37].”
BackgroundTay, B., Jung, Y., & Park, T. (2014) · Computers in Human Behavior · doi:10.1016/j.chb.2014.05.014 · Cited by 490 · cited 1×
“…features such as gender and accent (see [36] and [11] for a review), suggesting, for example, that voices may activate gender stereotypes [32, 38, 48] and influence the perceived credibility of a voice-based agent [1, 16], and that these perceptions may change depending on how human-like a voice…”
Background"What can i help you with?": infrequent users' experiences of intelligent personal assistants
Cowan, B. R., Pantidi, N., Coyle, D., Morrissey, K., Clarke, P., Al-Shehri, S., Earley, D., & Bandeira, N. (2017) · Proceedings of the 19th International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3098279.3098539 · Cited by 351
The State of Speech in HCI: Trends, Themes and Challenges
Clark, L., Doyle, P., Garaialde, D., Gilmartin, E., Schlögl, S., Edlund, J., Aylett, M., Cabral, J., Munteanu, C., Edwards, J., et al. (2019) · Interacting with Computers · doi:10.1093/iwc/iwz016 · Cited by 193
At Your Service: Designing Voice Assistant Personalities to Improve Automotive User Interfaces
Braun, M., Mainz, A., Chadowitz, R., Pfleging, B., & Alt, F. (2019) · Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3290605.3300270 · Cited by 182 · cited 1×
“A more recent study in the design of a car navigation interface also found that drivers preferred personality traits that matched their own [7].”
BackgroundMapping Perceptions of Humanness in Intelligent Personal Assistant Interaction
Doyle, P. R., Edwards, J., Dumbleton, O., Clark, L., & Cowan, B. R. (2019) · Proceedings of the 21st International Conference on Human-Computer Interaction with Mobile Devices and Services · doi:10.1145/3338286.3340116 · Cited by 100
Wagner, P., Beskow, J., Betz, S., Edlund, J., Gustafson, J., Eje Henter, G., Le Maguer, S., Malisz, Z., Székely, É., Tånnander, C., et al. (2019) · 10th ISCA Workshop on Speech Synthesis (SSW 10) · doi:10.21437/ssw.2019-19 · Cited by 74 · cited 9×
“However, speech technology is advancing so rapidly that the state-of-the-art is likely outpacing our own publishing cycles [41,49].”
BackgroundInfluentialA Large Inclusive Study of Human Listening Rates
Bragg, D., Bennett, C., Reinecke, K., & Ladner, R. (2018) · Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3173574.3174018 · Cited by 43
Cited by
Voice in Human–Agent Interaction: A Survey
Seaborn, K., Miyake, N. P., Pennefather, P., & Otake-Matsuura, M. (2022) · ACM Computing Surveys · doi:10.1145/3386867 · Cited by 249
“They concluded that “the variation... between how voices ranked... underscores that no single metric is sufficient for evaluating long-form speech” [9, 20].”
BackgroundSeymour, W., & Van Kleek, M. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479515 · Cited by 94
Firefox Voice: An Open and Extensible Voice Assistant Built Upon the Web
Cambre, J., Williams, A. C., Razi, A., Bicking, I., Wallin, A., Tsai, J., Kulkarni, C., & Kaye, J. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445409 · Cited by 39
“Building upon this related work and our own prior explorations in the voice products space [3, 11, 72, 80, 81], we took an iterative approach to the development of Firefox Voice.”
MethodSelf-citationImpact of Voice Fidelity on Decision Making: A Potential Dark Pattern?
Dubiel, M., Sergeeva, A., & Leiva, L. A. (2024) · Proceedings of the 29th International Conference on Intelligent User Interfaces · doi:10.1145/3640543.3645202 · Cited by 16
Kang, E. J., Kim, H., Kim, H., Fussell, S. R., & Kim, J. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711111 · Cited by 9
Metadata
- Authors
- Cambre, J., Colnago, J., Maddock, J., Tsai, J., & Kaye, J.
- Venue
- Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems
- Publisher
- ACM
- Published
- 2020-04-21
- Pages
- 1-13
- OpenAlex
- W3029538415
- Cited by
- 65
- References
- 10
- FWCI
- 3.02
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.