mlsanityData to 14 Oct 2026

End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator

arXiv 2210.16554 ↗First posted 29 Oct 2022cs.CL cs.SD eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

End-to-end spoken language understanding (SLU) suffers from the long-tail word problem. This paper exploits contextual biasing, a technique to improve the speech recognition of rare words, in end-to-end SLU systems. Specifically, a tree-constrained pointer generator (TCPGen), a powerful and efficient biasing model component, is studied, which leverages a slot shortlist with corresponding entities to extract biasing lists. Meanwhile, to bias the SLU model output slot distribution, a slot probability biasing (SPB) mechanism is proposed to calculate a slot distribution from TCPGen. Experiments on the SLURP dataset showed consistent SLU-F1 improvements using TCPGen and SPB, especially on unseen entities. On a new split by holding out 5 slot types for the test, TCPGen with SPB achieved zero-shot learning with an SLU-F1 score over 50% compared to baselines which can not deal with it. In addition to slot filling, the intent classification accuracy was also improved.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 31 of its 37 references that are in the map. First posted on arXiv 29 Oct 2022.

Builds on

31 of 37 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  5. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  7. 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
  8. 2020SLURP: A Spoken Language Understanding Resource Packagecited by 198
  9. 2018Deep context: end-to-end contextual speech recognitioncited by 137
  10. 2021Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusioncited by 101
  11. 2018Towards end-to-end spoken language understandingcited by 92
  12. 2020Contextual RNN-T For Open Domain ASRcited by 85
19 more
  1. 2020Deep Shallow Fusion for RNN-T Personalizationcited by 64
  2. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  3. 2021ESPnet-SLU: Advancing Spoken Language Understanding through ESPnetcited by 53
  4. 2020Class LM and word mapping for contextual biasing in End-to-End ASRcited by 42
  5. 2020Leveraging Unpaired Text Data for Training End-to-End Speech-to-Intent Systemscited by 38
  6. 2021Tree-constrained Pointer Generator for End-to-end Contextual Speech Recognitioncited by 32
  7. 2020End-to-End Neural Transformer Based Spoken Language Understandingcited by 31
  8. 2021Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognitioncited by 30
  9. 2018Contextual Speech Recognition with Difficult Negative Training Examplescited by 28
  10. 2018End-to-end contextual speech recognition using class language models and a token passing decodercited by 26
  11. 2020Tie Your Embeddings Down: Cross-Modal Latent Spaces for End-to-end Spoken Language Understandingcited by 23
  12. 2021Integration of Pre-trained Networks with Continuous Token Interface for End-to-End Spoken Language Understandingcited by 22
  13. 2022Tree-constrained Pointer Generator with Graph Neural Network Encodings for Contextual Speech Recognitioncited by 17
  14. 2020Speech to Text Adaptation: Towards an Efficient Cross-Modal Distillationcited by 11
  15. 2022Minimising Biasing Word Errors for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 11
  16. 2021Do as I mean, not as I say: Sequence Loss Training for Spoken Language Understandingcited by 9
  17. 2021Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speechcited by 6
  18. 2022Neural-FST Class Language Model for End-to-End Speech Recognitioncited by 6
  19. 2021On joint training with interfaces for spoken language understandingcited by 5

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 1.

6 papers.

  1. 2023Can Contextual Biasing Remain Effective with Whisper and GPT-2?cited by 21
  2. 2023Graph Neural Networks for Contextual ASR with the Tree-Constrained Pointer Generatorcited by 6
  3. 2023Knowledge-Aware Audio-Grounded Generative Slot Filling for Limited Annotated Datacited by 3
  4. 2023Speech-based Slot Filling using Large Language Modelscited by 3
  5. 2024An efficient text augmentation approach for contextualized Mandarin speech recognitioncited by 2
  6. 2023Is one brick enough to break the wall of spoken dialogue state tracking?cited by 1