Utterance-level Intent Recognition from Keywords

TL;DR

This paper introduces a low-power, noise-robust utterance-level intent recognition system using keyword sequences and multiple feature types, suitable for always-on devices with limited resources.

Contribution

It proposes a novel keyword sequence-based intent classification method with multi-feature fusion, tested on a new internal dataset, enhancing noise robustness and efficiency.

Findings

Achieved noise-robust intent classification across domains.

Demonstrated effectiveness on the new AMIE dataset.

System suitable for low-power, always-on applications.

Abstract

This paper focuses on wake on intent (WOI) techniques for platforms with limited compute and memory. Our approach of utterance-level intent classification is based on a sequence of keywords in the utterance instead of a single fixed key phrase. The keyword sequence is transformed into four types of input features, namely acoustics, phones, word2vec and speech2vec for individual intent learning and then fused decision making. If a wake intent is detected, it will trigger the power-costly ASR afterwards. The system is trained and tested on a newly collected internal dataset in Intel called AMIE, which will be reported in this paper for the first time. It is demonstrated that our novel technique with the representation of the key-phrases successfully achieved a noise robust intent classification in different domains including in-car human-machine communications. The wake on intent system will be low-power and low-complexity, which makes it suitable for always on operations in real life hardware-based applications.