mlsanityData to 7 Oct 2026

Towards Reducing the Need for Speech Training Data To Build Spoken Language Understanding Systems

arXiv 2203.00006 ↗First posted 26 Feb 2022cs.CL cs.SD eess.AScited by 20

Not on the map. Why?

Abstract (arXiv)

The lack of speech data annotated with labels required for spoken language understanding (SLU) is often a major hurdle in building end-to-end (E2E) systems that can directly process speech inputs. In contrast, large amounts of text data with suitable labels are usually available. In this paper, we propose a novel text representation and training methodology that allows E2E SLU systems to be effectively constructed using these text resources. With very limited amounts of additional speech, we show that these models can be further improved to perform at levels close to similar systems built on the full speech datasets. The efficacy of our proposed approach is demonstrated on both intent and entity tasks using three different SLU datasets. With text-only training, the proposed system achieves up to 90% of the performance possible with full speech training. With just an additional 10% of speech data, these models significantly improve further to 97% of full performance.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 19 of its 28 references that are in the map. First posted on arXiv 26 Feb 2022.

Builds on

19 of 28 references.

References · 19

  1. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  2. 2018Streaming End-to-end Speech Recognition For Mobile Devicescited by 230
  3. 2019Speech Model Pre-training for End-to-End Spoken Language Understandingcited by 191
  4. 2018Exploring Architectures, Data and Units For Streaming End-to-End Speech Recognition with RNN-Transducercited by 95
  5. 2018Towards end-to-end spoken language understandingcited by 92
  6. 2019Improving RNN Transducer Modeling for End-to-End Speech Recognitioncited by 68
  7. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  8. 2019Joint Speech Recognition and Speaker Diarization via Sequence Transductioncited by 49
  9. 2021Advancing RNN Transducer Technology for Speech Recognitioncited by 44
  10. 2020Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systemscited by 38
  11. 2020End-to-End Neural Transformer Based Spoken Language Understandingcited by 31
  12. 2019Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portabilitycited by 29
7 more
  1. 2019Using Speech Synthesis to Train End-to-End Spoken Language Understanding Modelscited by 24
  2. 2020End-to-End Spoken Language Understanding Without Full Transcriptscited by 19
  3. 2020Improving End-to-End Speech-to-Intent Classification with Reptilecited by 17
  4. 2019End-to-end architectures for ASR-free spoken language understandingcited by 11
  5. 2020Large-scale Transfer Learning for Low-resource Spoken Language Understandingcited by 11
  6. 2020HarperValleyBank: A Domain-Specific Spoken Dialog Corpuscited by 10
  7. 2021RNN Transducer Models For Spoken Language Understandingcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 11; 2024: 5; 2025: 2; 2026: 1.

20 papers.

Sort:

  1. 2023End-to-End Speech Recognition: A Surveycited by 127
  2. 2022JOIST: A Joint Speech and Text Streaming Model For ASRcited by 24
  3. 2023Massively Multilingual Shallow Fusion with Large Language Modelscited by 10
  4. 2023JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognitioncited by 9
  5. 2023Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Targetcited by 6
  6. 2025Exploring Fine-Tuning of Large Audio Language Models for Spoken Language Understanding under Limited Speech Datacited by 6
  7. 2023Zero-Shot End-to-End Spoken Language Understanding via Cross-Modal Selective Self-Trainingcited by 5
  8. 2023Text-only Domain Adaptation using Unified Speech-Text Representation in Transducercited by 5
  9. 2023Improving Joint Speech-Text Representations Without Alignmentcited by 4
  10. 2024Effective Text Adaptation for LLM-based ASR through Soft Prompt Fine-Tuningcited by 4
  11. 2024Text Injection for Neural Contextual Biasingcited by 3
  12. 2024Cascaded Cross-Modal Transformer for Audio-Textual Classificationcited by 2
8 more
  1. 2024ASTRA: Aligning Speech and Text Representations for Asr without Samplingcited by 2
  2. 2023EM-Network: Oracle Guided Self-distillation for Sequence Learningcited by 1
  3. 2023Exploring the Viability of Synthetic Audio Data for Audio-Based Dialogue State Trackingcited by 1
  4. 2025Joint Speech and Text Training for LLM-Based End-to-End Spoken Dialogue State Trackingcited by 1
  5. 2023End-to-End Open Vocabulary Keyword Search With Multilingual Neural Representationscited by 0
  6. 2023Text-Only Domain Adaptation for End-to-End Speech Recognition through Down-Sampling Acoustic Representationcited by 0
  7. 2024Written Term Detection Improves Spoken Term Detectioncited by 0
  8. 2026Text-Utilization for Encoder-dominated Speech Recognition Modelscited by 0