Projects per year
Abstract
Hyperarticulation is a speech adaptation that consists of adopting a clearer form of speech in an attempt to improve recognition levels. However, it has the opposite effect when talking to ASR systems, as they are not trained with such kind of speech. We present approaches for automatic detection of hyperarticulation, which can be used to improve the performance of spoken dialog systems. We performed experiments on Let’s Go data, using multiple feature sets and two classification approaches. Many relevant features are speaker dependent. Thus, we used the first turn in each dialog as the reference for the speaker, since it is typically not hyperarticulated. Our best results were above 80 % accuracy, which represents an improvement of at least 11.6 % points over previously obtained results on similar data. We also assessed the classifiers’ performance in scenarios where hyperarticulation is rare, achieving around 98 % accuracy using different confidence thresholds.
Original language | English |
---|---|
Title of host publication | Advances in Speech and Language Technologies for Iberian Languages |
Subtitle of host publication | Third International Conference, IberSPEECH 2016, Lisbon, Portugal, November 23-25, 2016, Proceedings |
Editors | Alberto Abad, Alfonso Ortega, António Teixeira, Carmen García Mateo, Carlos D. Martínez Hinarejos, Fernando Perdigão, Fernando Batista, Nuno Mamede |
Publisher | Springer Nature Switzerland AG |
Pages | 182-191 |
ISBN (Electronic) | 978-3-319-49169-1 |
ISBN (Print) | 978-3-319-49168-4 |
DOIs | |
Publication status | Published - Nov 2016 |
Externally published | Yes |
Event | International Conference on Advances in Speech and Language Technologies for Iberian Languages - Lisbon, Portugal Duration: 23 Nov 2016 → 25 Nov 2016 https://link.springer.com/conference/iberspeech |
Publication series
Series | Lecture Notes in Computer Science book series |
---|---|
Volume | volume 10077 |
Series | Lecture Notes in Artificial Intelligence (subseries) |
---|---|
Volume | volume 10077 |
Conference
Conference | International Conference on Advances in Speech and Language Technologies for Iberian Languages |
---|---|
Abbreviated title | IberSPEECH 2016 |
Country/Territory | Portugal |
City | Lisbon |
Period | 23/11/16 → 25/11/16 |
Internet address |
Keywords
- Hyperarticulation
- Speech
- Let’s Go
Fingerprint
Dive into the research topics of 'Automatic Detection of Hyperarticulated Speech'. Together they form a unique fingerprint.Projects
- 1 Finished
-
Rage: Realising an Applied Gaming Eco-system
Westera, W., Georgiadis, K., Saveski, G., van Lankveld, G., Bahreini, K., van der Vegt, W., Berkhout, J., Nyamsuren, E., Kluijfhout, E. & Nadolski, R.
1/02/15 → 31/07/19
Project: Research