mlsanityData to 7 Oct 2026

End2End Acoustic to Semantic Transduction

arXiv 2102.01013 ↗First posted 1 Feb 2021cs.CL cs.SD eess.AScited by 10

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose a novel end-to-end sequence-to-sequence spoken language understanding model using an attention mechanism. It reliably selects contextual acoustic features in order to hypothesize semantic contents. An initial architecture capable of extracting all pronounced words and concepts from acoustic spans is designed and tested. With a shallow fusion language model, this system reaches a 13.6 concept error rate (CER) and an 18.5 concept value error rate (CVER) on the French MEDIA corpus, achieving an absolute 2.8 points reduction compared to the state-of-the-art. Then, an original model is proposed for hypothesizing concepts and their values. This transduction reaches a 15.4 CER and a 21.6 CVER without any new type of context.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 1 Feb 2021.

Builds on

17 of 30 references.

References · 17

  1. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  2. 2015Listen, Attend and Spellcited by 542
  3. 2019vq-wav2vec: Self-Supervised Learning of Discrete Speech Representationscited by 335
  4. 2015On Using Monolingual Corpora in Neural Machine Translationcited by 149
  5. 2015End-to-End Attention-based Large Vocabulary Speech Recognitioncited by 148
  6. 2016Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Fillingcited by 137
  7. 2018Towards end-to-end spoken language understandingcited by 92
  8. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  9. 2014End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Resultscited by 68
  10. 2018From Audio to Semantics: Approaches to end-to-end spoken language understandingcited by 63
  11. 2019Espresso: A Fast End-to-end Neural Speech Recognition Toolkitcited by 31
  12. 2019Curriculum-based transfer learning for an effective end-to-end spoken language understanding and domain portabilitycited by 29
5 more
  1. 2018End-to-end Speech Recognition with Word-based RNN Language Modelscited by 23
  2. 2020Improved Speech Representations with Multi-Target Autoregressive Predictive Codingcited by 23
  3. 2020Dialogue history integration into end-to-end signal-to-concept spoken language understanding systemscited by 10
  4. 2020CSTNet: Contrastive Speech Translation Network for Self-Supervised Speech Representation Learningcited by 6
  5. 2017ASR error management for improving spoken language understandingcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 3; 2023: 3; 2024: 1; 2025: 0; 2026: 1.

10 papers.

  1. 2023LeBenchmark 2.0: a Standardized, Replicable and Enhanced Framework for Self-supervised Representations of French Speechcited by 17
  2. 2021Where are we in semantic concept extraction for Spoken Language Understanding?cited by 11
  3. 2021Speech2Slot: An End-to-End Knowledge-based Slot Filling from Speechcited by 6
  4. 2022ASR-Generated Text for Language Model Pre-training Applied to Speech Taskscited by 6
  5. 2022Toward Low-Cost End-to-End Spoken Language Understandingcited by 3
  6. 2024New Semantic Task for the French Spoken Language Understanding MEDIA Benchmarkcited by 2
  7. 2026Pantagruel: Unified Self-Supervised Encoders for French Text and Speechcited by 2
  8. 2023Leveraging Multilingual Self-Supervised Pretrained Models for Sequence-to-Sequence End-to-End Spoken Language Understandingcited by 1
  9. 2023Is one brick enough to break the wall of spoken dialogue state tracking?cited by 1
  10. 2022Vers la compr'ehension automatique de la parole bout-en-bout `a moindre effortcited by 0