mlsanityData to 14 Oct 2026

Enhancing End-to-End Conversational Speech Translation Through Target Language Context Utilization

arXiv 2309.15686 ↗First posted 27 Sep 2023cs.CL cs.SD eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Incorporating longer context has been shown to benefit machine translation, but the inclusion of context in end-to-end speech translation (E2E-ST) remains under-studied. To bridge this gap, we introduce target language context in E2E-ST, enhancing coherence and overcoming memory constraints of extended audio segments. Additionally, we propose context dropout to ensure robustness to the absence of context, and further improve performance by adding speaker information. Our proposed contextual E2E-ST outperforms the isolated utterance-based E2E-ST approach. Lastly, we demonstrate that in conversational speech, contextual information primarily contributes to capturing context style, as well as resolving anaphora and named entities.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 20 of its 39 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

20 of 39 references.

References · 20

  1. 2017Attention Is All You Needcited by 60,361
  2. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,989
  4. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,863
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  6. 2019SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognitioncited by 1,380
  7. 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
  8. 2018Context-Aware Neural Machine Translation Learns Anaphora Resolutioncited by 97
  9. 2020Serialized Output Training for End-to-End Overlapped Speech Recognitioncited by 87
  10. 2018Document-Level Neural Machine Translation with Hierarchical Attention Networkscited by 85
  11. 2018End-to-End Automatic Speech Translation of Audiobookscited by 65
  12. 2017Exploiting Cross-Sentence Context for Neural Machine Translationcited by 48
8 more
  1. 2020End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020cited by 31
  2. 2021Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformerscited by 25
  3. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  4. 2021Searchable Hidden Intermediates for End-to-End Models of Decomposable Sequence Taskscited by 24
  5. 2019Cross-Attention End-to-End ASR for Two-Party Conversationscited by 14
  6. 2023ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkitcited by 10
  7. 2022Context-aware Fine-tuning of Self-supervised Speech Modelscited by 7
  8. 2019Acoustic-to-Word Models with Conversational Context Informationcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Locate-and-Focus: Enhancing Terminology Translation in Speech Language Modelscited by 3
  2. 2025HENT-SRT: Hierarchical Efficient Neural Transducer with Self-Distillation for Joint Speech Recognition and Translationcited by 1
  3. 2026From Oracle to Noisy Context: Mitigating Contextual Exposure Bias in Speech-LLMscited by 0