mlsanityData to 7 Oct 2026

Transformer-based Model for ASR N-Best Rescoring and Rewriting

arXiv 2406.08207 ↗First posted 12 Jun 2024eess.AS cs.CL cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further processing by a search engine. For such applications, we propose a novel Transformer based model capable of rescoring and rewriting, by exploring full context of the N-best hypotheses in parallel. We also propose a new discriminative sequence training objective that can work well for both rescore and rewrite tasks. We show that our Rescore+Rewrite model outperforms the Rescore-only baseline, and achieves up to an average 8.6% relative Word Error Rate (WER) reduction over the ASR system by itself.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 12 Jun 2024.

Builds on

22 of 31 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  5. 2021WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkitcited by 123
  6. 2015EESEN: End-to-End Speech Recognition using Deep RNN Models and WFST-based Decodingcited by 73
  7. 2017Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Modelscited by 68
  8. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  9. 2019Two-Pass End-to-End Speech Recognitioncited by 62
  10. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  11. 2022RescoreBERT: Discriminative Speech Recognition Rescoring with BERTcited by 34
  12. 2021Transformer Based Deliberation for Two-Pass Speech Recognitioncited by 29
10 more
  1. 2019An Empirical Study of Efficient ASR Rescoring with Transformerscited by 11
  2. 2019Connecting and Comparing Language Model Interpolation Techniquescited by 10
  3. 2022Improving Deliberation by Text-Only and Semi-Supervised Trainingcited by 10
  4. 2024Synthetic Query Generation using Large Language Models for Virtual Assistantscited by 9
  5. 2021Error-driven Pruning of Language Models for Virtual Assistantscited by 8
  6. 2022Space-Efficient Representation of Entity-centric Query Language Modelscited by 7
  7. 2021Lattention: Lattice-attention in ASR rescoringcited by 6
  8. 2023Acoustic Model Fusion for End-to-end Speech Recognitioncited by 6
  9. 2023Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunitiescited by 4
  10. 2023Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistantscited by 2

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 2.

3 papers.

  1. 2024ProGRes: Prompted Generative Rescoring on ASR n-Bestcited by 5
  2. 2025Audio-Conditioned Diffusion LLMs for ASR and Deliberation Processingcited by 1
  3. 2025Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correctioncited by 0