Automatic Speech Recognition: Do Emotions Matter?
Abstract
By leveraging the advancements in Natural Language Processing and Cognitive Computing, conversational artificial intelligence (AI) has become more mature over the last years. It serves humans in a broad range of applications in business enterprises, government, health-care, and entertaining, and it is getting more embedded into peoples' lives. However, despite the recent improvements, we are still far away from a robust or general AI comparable to human intelligence, especially when it comes to adaptive intelligence able to settle into non-standard and noisy environments. In this paper, we bring to light that emotion in speech negatively affects automatic speech recognition and automatic human inputs understanding. Therefore, emotion is to be considered as a noise compromising the understanding of what the user says and consequently messing up the whole interaction with conversational technologies. For this study, Google Cloud Speech-to-Text and IBM Watson Speech-to-Text have been used.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prior research reports WER measurements for several of the vendors included in this study.
“Summary of Word Error Rate measurements of diferent services from related research”
From Measuring the Accuracy of Automatic Speech Recognition Solutions (2023) · cites this paper as Catania et al. 2019
Cites
Picard, R. W. (1997) · MIT Press · doi:10.7551/mitpress/1140.001.0001 · Cited by 7,382 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Measuring the Accuracy of Automatic Speech Recognition Solutions
Kuhn, K., Kersken, V., Reuter, B., Egger, N., & Zimmermann, G. (2023) · ACM Transactions on Accessible Computing · doi:10.1145/3636513 · Cited by 44 · see citing works
“Errors from capitalisation or grammatical cases are more common in languages other than English, but it is unclear whether these have an impact on the understandability of the text.”
Background
- Authors
- Catania, F., Crovari, P., Spitale, M., & Garzotto, F.
- Affiliations
- Politecnico di Milano (IT)
- Venue
- 2019 IEEE International Conference on Conversational Data & Knowledge Engineering (CDKE)
- Publisher
- IEEE
- Published
- 2019-12
- Pages
- 9-16
- OpenAlex
- W3000558177
- Cited by
- 7
- References
- 1
- Citations by year
- 2025: 1 · 2024: 1 · 2023: 3 · 2021: 2
- FWCI
- 0.19
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- BOA (University of Milano-Bicocca) (submittedVersion)
- Virtual Community of Pathological Anatomy (University of Castilla La Mancha) (submittedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Emotion and Mood Recognition
- Physical Sciences › Computer Science › Artificial Intelligence › Speech and dialogue systems
- Keywords
- speech recognition, emotion in speech, speech emotion recognition, conversational AI, speech-to-text, noisy environments
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
