Incremental processing of noisy user utterances in the spoken language understanding task

Stefan Constantin, Jan Niehues, Alex Waibel

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingAcademicpeer-review


The state-of-the-art neural network architectures make it possible to create spoken language understanding systems with high quality and fast processing time. One major challenge for real-world applications is the high latency of these systems caused by triggered actions with high executions times. If an action can be separated into subactions, the reaction time of the systems can be improved through incremental processing of the user utterance and starting subactions while the utterance is still being uttered. In this work, we present a model-agnostic method to achieve high quality in processing incrementally produced partial utterances. Based on clean and noisy versions of the ATIS dataset, we show how to create datasets with our method to create low-latency natural language understanding components. We get improvements of up to 47.91 absolute percentage points in the metric F1-score.
Original languageEnglish
Title of host publicationProceedings of the 5th Workshop on Noisy User-generated Text (W-NUT)
PublisherAssociation for Computational Linguistics (ACL)
Number of pages10
ISBN (Electronic)9781950737840
Publication statusPublished - 2019
Event5th Workshop on Noisy User-Generated Text - Hong Kong, China
Duration: 4 Nov 20194 Nov 2019
Conference number: 5


Workshop5th Workshop on Noisy User-Generated Text
Abbreviated titleW-NUT@EMNLP 2019
CityHong Kong


Dive into the research topics of 'Incremental processing of noisy user utterances in the spoken language understanding task'. Together they form a unique fingerprint.

Cite this