mlsanityData to 14 Oct 2026

A Study of Different Ways to Use The Conformer Model For Spoken Language Understanding

arXiv 2204.03879 ↗First posted 8 Apr 2022cs.CL cs.SD eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

SLU combines ASR and NLU capabilities to accomplish speech-to-intent understanding. In this paper, we compare different ways to combine ASR and NLU, in particular using a single Conformer model with different ways to use its components, to better understand the strengths and weaknesses of each approach. We find that it is not necessarily a choice between two-stage decoding and end-to-end systems which determines the best system for research or application. System optimization still entails carefully improving the performance of each component. It is difficult to prove that one direction is conclusively better than the other. In this paper, we also propose a novel connectionist temporal summarization (CTS) method to reduce the length of acoustic encoding sequences while improving the accuracy and processing speed of end-to-end models. This method achieves the same intent accuracy as the best two-stage SLU recognition with complicated and time-consuming decoding but does so at lower computational cost. This stacked end-to-end SLU system yields an intent accuracy of 93.97% for the SmartLights far-field set, 95.18% for the close-field set, and 99.71% for FluentSpeech.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 11 of its 24 references that are in the map. First posted on arXiv 8 Apr 2022.

Builds on

11 of 24 references.

References · 11

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 193
  4. 2018Towards end-to-end spoken language understandingcited by 92
  5. 2018Spoken Language Understanding on the Edgecited by 27
  6. 2019Using Speech Synthesis to Train End-to-End Spoken Language Understanding Modelscited by 24
  7. 2020Exploring Transfer Learning For End-to-End Spoken Language Understandingcited by 17
  8. 2020Large-scale Transfer Learning for Low-resource Spoken Language Understandingcited by 11
  9. 2021Rethinking End-to-End Evaluation of Decomposable Tasks: A Case Study on Spoken Language Understandingcited by 11
  10. 2020Semantic Complexity in End-to-End Spoken Language Understandingcited by 10
  11. 2022Three-Module Modeling For End-to-End Spoken Language Understanding Using Pre-trained DNN-HMM-Based Acoustic-Phonetic Modelcited by 3

Built on by

Not cited yet.