mlsanityData to 14 Oct 2026

RNN Transducer Models For Spoken Language Understanding

arXiv 2104.03842 ↗First posted 8 Apr 2021cs.CL cs.LG cs.SDcited by 7

Not on the map. Why?

Abstract (arXiv)

We present a comprehensive study on building and adapting RNN transducer (RNN-T) models for spoken language understanding(SLU). These end-to-end (E2E) models are constructed in three practical settings: a case where verbatim transcripts are available, a constrained case where the only available annotations are SLU labels and their values, and a more restrictive case where transcripts are available but not corresponding audio. We show how RNN-T SLU models can be developed starting from pre-trained automatic speech recognition (ASR) systems, followed by an SLU adaptation step. In settings where real audio data is not available, artificially synthesized speech is used to successfully adapt various SLU models. When evaluated on two SLU data sets, the ATIS corpus and a customer call center data set, the proposed models closely track the performance of other E2E models and achieve state-of-the-art results.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 18 of its 31 references that are in the map. First posted on arXiv 8 Apr 2021.

Builds on

18 of 31 references.

References · 18

  1. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 234
  2. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 193
  3. 2018Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducercited by 96
  4. 2018Towards end-to-end spoken language understandingcited by 92
  5. 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68
  6. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  7. 2019Joint Speech Recognition and Speaker Diarization via Sequence Transductioncited by 49
  8. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  9. 2020Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systemscited by 38
  10. 2020End-to-End Neural Transformer Based Spoken Language Understandingcited by 31
  11. 2019Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portabilitycited by 29
  12. 2019Using Speech Synthesis to Train End-to-End Spoken Language Understanding Modelscited by 24
6 more
  1. 2020End-to-End Spoken Language Understanding Without Full Transcriptscited by 19
  2. 2019Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge Distillationcited by 18
  3. 2020Improving End-to-End Speech-to-Intent Classification with Reptilecited by 17
  4. 2019High quality, lightweight and adaptable TTS using LPCNetcited by 11
  5. 2019End-to-end architectures for ASR-free spoken language understandingcited by 11
  6. 2020Large-scale Transfer Learning for Low-resource Spoken Language Understandingcited by 11

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 2.

7 papers.

  1. 2022Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systemscited by 20
  2. 2021Integrating Dialog History into End-to-End Spoken Language Understanding Systemscited by 9
  3. 2023Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Targetcited by 6
  4. 2021On joint training with interfaces for spoken language understandingcited by 5
  5. 2022Improving End-to-End Models for Set Prediction in Spoken Language Understandingcited by 0
  6. 2022A new data augmentation method for intent classification enhancement and its application on spoken conversation datasetscited by 0
  7. 2023Improving End-to-End Speech Processing by Efficient Text Data Utilization with Latent Synthesiscited by 0