mlsanityData to 7 Oct 2026

Exploring Phoneme-Level Speech Representations for End-to-End Speech Translation

arXiv 1906.01199 ↗First posted 4 Jun 2019cs.CL cs.SD eess.AScited by 15

Not on the map. Why?

Abstract (arXiv)

Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech representations is far more effective and efficient for translation than traditional frame-level speech features. Specifically, we generate phoneme labels for speech frames and average consecutive frames with the same label to create shorter, higher-level source sequences for translation. We see improvements of up to 5 BLEU on both our high and low resource language pairs, with a reduction in training time of 60%. Our improvements hold across multiple data sizes and two language pairs.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Jun 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 8; 2022: 3; 2023: 2; 2024: 1; 2025: 1.

15 papers.

Sort:

  1. 2021The Multilingual TEDx Corpus for Speech Recognition and Translationcited by 101
  2. 2021CTC-based Compression for Direct Speech Translationcited by 45
  3. 2021Large-Scale Self- and Semi-Supervised Learning for Speech Translationcited by 36
  4. 2022Revisiting End-to-End Speech-to-Text Translation From Scratchcited by 26
  5. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  6. 2021Speechformer: Reducing Information Loss in Direct Speech Translationcited by 15
  7. 2021On-the-Fly Aligned Data Augmentation for Sequence-to-Sequence ASRcited by 9
  8. 2021Pre-training for Spoken Language Understanding with Joint Textual and Phonetic Representation Learningcited by 6
  9. 2022AdaTranS: Adapting with Boundary-based Shrinking for End-to-End Speech Translationcited by 3
  10. 2021AlloST: Low-resource Speech Translation without Source Transcriptioncited by 2
  11. 2023Bridging the Granularity Gap for Acoustic Modelingcited by 2
  12. 2022Multiformer: A Head-Configurable Transformer-Based Model for Direct Speech Translationcited by 1
3 more
  1. 2023Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translationcited by 1
  2. 2024How do Hyenas deal with Human Speech? Speech Recognition and Translation with ConfHyenacited by 1
  3. 2025Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translationcited by 0