The reviewed record of science sign in
Pith

arxiv: 2011.12221 · v1 · pith:7KZ3GVUC · submitted 2020-11-24 · eess.AS

A light transformer for speech-to-intent applications

Reviewed by Pithpith:7KZ3GVUCopen to challenge →

classification eess.AS
keywords systemspeechlightmodeltransformerusersconditionslanguage
0
0 comments X
read the original abstract

Spoken language understanding (SLU) systems can make life more agreeable, safer (e.g. in a car) or can increase the independence of physically challenged users. However, due to the many sources of variation in speech, a well-trained system is hard to transfer to other conditions like a different language or to speech impaired users. A remedy is to design a user-taught SLU system that can learn fully from scratch from users' demonstrations, which in turn requires that the system's model quickly converges after only a few training samples. In this paper, we propose a light transformer structure by using a simplified relative position encoding with the goal to reduce the model size and improve efficiency. The light transformer works as an alternative speech encoder for an existing user-taught multitask SLU system. Experimental results on three datasets with challenging speech conditions prove our approach outperforms the existed system and other state-of-art models with half of the original model size and training time.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.