mlsanityData to 7 Oct 2026

Promptformer: Prompted Conformer Transducer for ASR

arXiv 2401.07360 ↗First posted 14 Jan 2024cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Context cues carry information which can improve multi-turn interactions in automatic speech recognition (ASR) systems. In this paper, we introduce a novel mechanism inspired by hyper-prompting to fuse textual context with acoustic representations in the attention mechanism. Results on a test set with multi-turn interactions show that our method achieves 5.9% relative word error rate reduction (rWERR) over a strong baseline. We show that our method does not degrade in the absence of context and leads to improvements even if the model is trained without context. We further show that leveraging a pre-trained sentence-piece model for context embedding generation can outperform an external BERT model.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 24 references that are in the map. First posted on arXiv 14 Jan 2024.

Builds on

18 of 24 references.

References · 18

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  3. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,355
  4. 2020Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognitioncited by 185
  5. 2018Deep context: end-to-end contextual speech recognitioncited by 136
  6. 2020Contextual RNN-T For Open Domain ASRcited by 85
  7. 2022HyperPrompt: Prompt-based Task-Conditioning of Transformerscited by 67
  8. 2022Contextual Adapters for Personalized Speech Recognition in Neural Transducerscited by 57
  9. 2021Context-Aware Transformer Transducer for Speech Recognitioncited by 56
  10. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  11. 2021Hierarchical Transformer-based Large-Context End-to-end ASR with Large-Context Knowledge Distillationcited by 12
  12. 2023PROCTER: PROnunciation-aware ConTextual adaptER for personalized speech recognition in neural transducerscited by 10
6 more
  1. 2022Towards End-to-End Integration of Dialog History for Improved Spoken Language Understandingcited by 8
  2. 2021Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understandingcited by 5
  3. 2022Improving Transformer-based Conversational ASR by Inter-Sentential Attention Mechanismcited by 4
  4. 2023Dialog act guided contextual adapter for personalized speech recognitioncited by 4
  5. 2023Joint Modelling of Spoken Language Understanding Tasks with Integrated Dialog Historycited by 3
  6. 2022Contextual-Utterance Training for Automatic Speech Recognitioncited by 1

Built on by

Cited by year

Citing papers per year: 2024: 3.

3 papers.

  1. 2024Improving Domain-Specific ASR with LLM-Generated Contextual Descriptionscited by 6
  2. 2024Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrievalcited by 3
  3. 2024An Efficient Self-Learning Framework For Interactive Spoken Dialog Systemscited by 0