mlsanityData to 7 Oct 2026

Bilingual End-to-End ASR with Byte-Level Subwords

arXiv 2205.00485 ↗First posted 1 May 2022cs.CL cs.SD eess.AScited by 4

Not on the map. Why?

Abstract (arXiv)

In this paper, we investigate how the output representation of an end-to-end neural network affects multilingual automatic speech recognition (ASR). We study different representations including character-level, byte-level, byte pair encoding (BPE), and byte-level byte pair encoding (BBPE) representations, and analyze their strengths and weaknesses. We focus on developing a single end-to-end model to support utterance-based bilingual ASR, where speakers do not alternate between two languages in a single utterance but may change languages across utterances. We conduct our experiments on English and Mandarin dictation tasks, and we find that BBPE with penalty schemes can improve utterance-based bilingual ASR performance by 2% to 5% relative even with smaller number of outputs and fewer parameters. We conclude with analysis that indicates directions for further improving multilingual ASR.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 12 of its 18 references that are in the map. First posted on arXiv 1 May 2022.

Builds on

12 of 18 references.

References · 12

  1. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  2. 2015Listen, Attend and Spellcited by 542
  3. 2021ByT5: Towards a token-free future with pre-trained byte-to-byte modelscited by 504
  4. 2019Neural Machine Translation with Byte-Level Subwordscited by 115
  5. 2020Massively Multilingual ASR: 50 Languages, 1 Model, 1 Billion Parameterscited by 110
  6. 2019Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Modelcited by 92
  7. 2018Bytes are All You Need: End-to-End Multilingual Speech Recognition and Synthesis with Bytescited by 54
  8. 2015Multilingual Language Processing From Bytescited by 26
  9. 2020Streaming End-to-End Bilingual ASR Systems with Joint Language Identificationcited by 20
  10. 2018A Comparison of Modeling Units in Sequence-to-Sequence Speech Recognition with the Transformer on Mandarin Chinesecited by 10
  11. 2020Online Automatic Speech Recognition with Listen, Attend and Spell Modelcited by 10
  12. 2018A comparable study of modeling units for end-to-end Mandarin speech recognitioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

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

4 papers.

  1. 2022Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generationcited by 5
  2. 2024Optimizing Byte-level Representation for End-to-end ASRcited by 1
  3. 2024Romanization Encoding For Multilingual ASRcited by 1
  4. 2026BBPE16: UTF-16-based byte-level byte-pair encoding for improved multilingual speech recognitioncited by 0