Wöllmer M, Schuller B, Batliner A, Steidl S, Seppi D (2011)
Publication Language: English
Publication Type: Journal article, Original article
Publication year: 2011
Original Authors: Wöllmer Martin, Schuller Björn, Batliner Anton, Steidl Stefan, Seppi Dino
Publisher: Association for Computing Machinary, Inc.
Book Volume: 7
Article Number: 12
Journal Issue: 4
URI: http://www5.informatik.uni-erlangen.de/Forschung/Publikationen/2011/Woellmer11-TDO.pdf
In this article, we focus on keyword detection in children's speech as it is needed in voice command systems. We use the FAU Aibo Emotion Corpus which contains emotionally colored spontaneous children's speech recorded in a child-robot interaction scenario and investigate various recent key-word spotting techniques. As the principle of bidirectional Long Short-Term Memory (BLSTM) is known to be well-suited for context-sensitive phoneme prediction, we incorporate a BLSTM network into a Tandem model for exible coarticulation modeling in children's speech. Our experiments reveal that the Tandem model prevails over a triphone-based Hidden Markov Model approach.
APA:
Wöllmer, M., Schuller, B., Batliner, A., Steidl, S., & Seppi, D. (2011). Tandem decoding of children's speech for keyword detection in a child-robot interaction scenario. ACM Transactions on Speech and Language Processing, 7(4). https://doi.org/10.1145/1998384.1998386
MLA:
Wöllmer, Martin, et al. "Tandem decoding of children's speech for keyword detection in a child-robot interaction scenario." ACM Transactions on Speech and Language Processing 7.4 (2011).
BibTeX: Download