mlsanityData to 14 Oct 2026

Phonetically-Augmented Discriminative Rescoring for Voice Search Error Correction

arXiv 2506.06117 ↗First posted 6 Jun 2025cs.CL cs.AI cs.IRcited by 0

Not on the map. Why?

Abstract (arXiv)

End-to-end (E2E) Automatic Speech Recognition (ASR) models are trained using paired audio-text samples that are expensive to obtain, since high-quality ground-truth data requires human annotators. Voice search applications, such as digital media players, leverage ASR to allow users to search by voice as opposed to an on-screen keyboard. However, recent or infrequent movie titles may not be sufficiently represented in the E2E ASR system's training data, and hence, may suffer poor recognition. In this paper, we propose a phonetic correction system that consists of (a) a phonetic search based on the ASR model's output that generates phonetic alternatives that may not be considered by the E2E system, and (b) a rescorer component that combines the ASR model recognition and the phonetic alternatives, and select a final system output. We find that our approach improves word error rate between 4.4 and 7.6% relative on benchmarks of popular movie titles over a series of competitive baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 21 of its 35 references that are in the map. First posted on arXiv 6 Jun 2025.

Builds on

21 of 35 references.

References · 21

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  3. 2023End-to-End Speech Recognition: A Surveycited by 129
  4. 2020Internal Language Model Estimation for Domain-Adaptive End-to-End Speech Recognitioncited by 80
  5. 2019Recognizing long-form speech using streaming end-to-end modelscited by 77
  6. 2017Minimum Word Error Rate Training for Attention-based Sequence-to-Sequence Modelscited by 68
  7. 2019A spelling correction model for end-to-end speech recognitioncited by 63
  8. 2019Correction of Automatic Speech Recognition with Transformer Sequence-to-sequence Modelcited by 52
  9. 2021Transformer Based Deliberation for Two-Pass Speech Recognitioncited by 29
  10. 2021CTC Variations Through New WFST Topologiescited by 17
  11. 2019Connecting and Comparing Language Model Interpolation Techniquescited by 10
  12. 2022Improving Deliberation by Text-Only and Semi-Supervised Trainingcited by 10
9 more
  1. 2024Synthetic Query Generation using Large Language Models for Virtual Assistantscited by 9
  2. 2021Error-driven Pruning of Language Models for Virtual Assistantscited by 8
  3. 2021A Discriminative Entity-Aware Language Model for Virtual Assistantscited by 7
  4. 2022Space-Efficient Representation of Entity-centric Query Language Modelscited by 7
  5. 2023Acoustic Model Fusion for End-to-end Speech Recognitioncited by 6
  6. 2023Modeling Spoken Information Queries for Virtual Assistants: Open Problems, Challenges and Opportunitiescited by 4
  7. 2023Application-Agnostic Language Modeling for On-Device ASRcited by 3
  8. 2024Transformer-based Model for ASR N-Best Rescoring and Rewritingcited by 3
  9. 2023Server-side Rescoring of Spoken Entity-centric Knowledge Queries for Virtual Assistantscited by 2

Built on by

Not cited yet.