mlsanityData to 14 Oct 2026

Improving End-to-end Speech Recognition with Pronunciation-assisted Sub-word Modeling

arXiv 1811.04284 ↗First posted 10 Nov 2018cs.CLcited by 10

Not on the map. Why?

Abstract (arXiv)

Most end-to-end speech recognition systems model text directly as a sequence of characters or sub-words. Current approaches to sub-word extraction only consider character sequence frequencies, which at times produce inferior sub-word segmentation that might lead to erroneous speech recognition output. We propose pronunciation-assisted sub-word modeling (PASM), a sub-word extraction method that leverages the pronunciation information of a word. Experiments show that the proposed method can greatly improve upon the character-based baseline, and also outperform commonly used byte-pair encoding methods.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 10 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 0; 2023: 1; 2024: 4.

10 papers.

  1. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  2. 2021Recent Advances in End-to-End Automatic Speech Recognitioncited by 140
  3. 2023End-to-End Speech Recognition: A Surveycited by 129
  4. 2021Hierarchical Conditional End-to-End ASR with CTC and Multi-Granular Subword Unitscited by 13
  5. 2021Acoustic Data-Driven Subword Modeling for End-to-End Speech Recognitioncited by 11
  6. 2024A cost minimization approach to fix the vocabulary size in a tokenizer for an End-to-End ASR systemcited by 1
  7. 2024Enhancing CTC-based speech recognition with diverse modeling unitscited by 1
  8. 2021Improving Word Recognition in Speech Transcriptions by Decision-level Fusion of Stemming and Two-way Phoneme Pruningcited by 0
  9. 2024Byte Pair Encoding Is All You Need For Automatic Bengali Speech Recognitioncited by 0
  10. 2024Transducers with Pronunciation-aware Embeddings for Automatic Speech Recognitioncited by 0