# Cascade versus Direct Speech Translation: Do the Differences Still Make a Difference?

arXiv: https://arxiv.org/abs/2106.01045 · HTML: https://mlsanity.com/paper/2106.01045/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 72 references that are in the map.
- First posted on arXiv 2 Jun 2021.

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [TED-LIUM 3: twice as much data and corpus repartition for experiments on speaker adaptation](https://mlsanity.com/paper/1805.04699/) (2018)
- [How2: A Large-scale Dataset for Multimodal Language Understanding](https://mlsanity.com/paper/1811.00347/) (2018)
- [Sequence-to-Sequence Models Can Directly Translate Foreign Speech](https://mlsanity.com/paper/1703.08581/) (2017)
- [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](https://mlsanity.com/paper/1911.03167/) (2019)
- [Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1612.01744/) (2016)
- [ESPnet-ST: All-in-One Speech Translation Toolkit](https://mlsanity.com/paper/2004.10234/) (2020)
- [Speech Translation and the End-to-End Promise: Taking Stock of Where We Are](https://mlsanity.com/paper/2004.06358/) (2020)
- [Pre-training on high-resource speech recognition improves low-resource speech-to-text translation](https://mlsanity.com/paper/1809.01431/) (2018)
- [End-to-End Automatic Speech Translation of Audiobooks](https://mlsanity.com/paper/1802.04200/) (2018)
- [End-to-End Speech Translation with Knowledge Distillation](https://mlsanity.com/paper/1904.08075/) (2019)
- [Leveraging Weakly Supervised Data to Improve End-to-End Speech-to-Text Translation](https://mlsanity.com/paper/1811.02050/) (2018)
- [Bridging the Modality Gap for Speech-to-Text Translation](https://mlsanity.com/paper/2010.14920/) (2020)
- [Tied Multitask Learning for Neural Speech Translation](https://mlsanity.com/paper/1802.06655/) (2018)
- [A Comparative Study on End-to-end Speech to Text Translation](https://mlsanity.com/paper/1911.08870/) (2019)
- [End-to-End Speech-Translation with Knowledge Distillation: FBK@IWSLT2020](https://mlsanity.com/paper/2006.02965/) (2020)
- [Self-Attentional Acoustic Models](https://mlsanity.com/paper/1803.09519/) (2018)
- [Improving sequence-to-sequence speech recognition training with on-the-fly data augmentation](https://mlsanity.com/paper/1910.13296/) (2019)
- [On Using SpecAugment for End-to-End Speech Translation](https://mlsanity.com/paper/1911.08876/) (2019)
- [One-To-Many Multilingual End-to-end Speech Translation](https://mlsanity.com/paper/1910.03320/) (2019)
- [XNMT: The eXtensible Neural Machine Translation Toolkit](https://mlsanity.com/paper/1803.00188/) (2018)
- [Robust Neural Machine Translation for Clean and Noisy Speech Transcripts](https://mlsanity.com/paper/1910.10238/) (2019)
- [Self-Attentional Models for Lattice Inputs](https://mlsanity.com/paper/1906.01617/) (2019)
- [Quality expectations of machine translation](https://mlsanity.com/paper/1803.08409/) (2018)

## Built on by (most cited first, 30 of 54)

- [Hallucinations in Large Multilingual Translation Models](https://mlsanity.com/paper/2303.16104/) (2023)
- [Cross-modal Contrastive Learning for Speech Translation](https://mlsanity.com/paper/2205.02444/) (2022)
- [SHAS: Approaching optimal Segmentation for End-to-End Speech Translation](https://mlsanity.com/paper/2202.04774/) (2022)
- [Pre-training for Speech Translation: CTC Meets Optimal Transport](https://mlsanity.com/paper/2301.11716/) (2023)
- [Under the Morphosyntactic Lens: A Multifaceted Evaluation of Gender Bias in Speech Translation](https://mlsanity.com/paper/2203.09866/) (2022)
- [Speech Translation with Speech Foundation Models and Large Language Models: What is There and What is Missing?](https://mlsanity.com/paper/2402.12025/) (2024)
- [How "Real" is Your Real-Time Simultaneous Speech-to-Text Translation System?](https://mlsanity.com/paper/2412.18495/) (2024)
- [Understanding and Bridging the Modality Gap for Speech Translation](https://mlsanity.com/paper/2305.08706/) (2023)
- [Recent Advances in Direct Speech-to-text Translation](https://mlsanity.com/paper/2306.11646/) (2023)
- [Pushing the Limits of Zero-shot End-to-End Speech Translation](https://mlsanity.com/paper/2402.10422/) (2024)
- [Non-Parametric Domain Adaptation for End-to-End Speech Translation](https://mlsanity.com/paper/2205.11211/) (2022)
- [Simple and Effective Unsupervised Speech Translation](https://mlsanity.com/paper/2210.10191/) (2022)
- [LLaST: Improved End-to-end Speech Translation System Leveraged by Large Language Models](https://mlsanity.com/paper/2407.15415/) (2024)
- [ESPnet-ST-v2: Multipurpose Spoken Language Translation Toolkit](https://mlsanity.com/paper/2304.04596/) (2023)
- [Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoring](https://mlsanity.com/paper/2109.04411/) (2021)
- [End-to-End Speech-to-Text Translation: A Survey](https://mlsanity.com/paper/2312.01053/) (2023)
- [Who Are We Talking About? Handling Person Names in Speech Translation](https://mlsanity.com/paper/2205.06755/) (2022)
- [Direct Speech Translation for Automatic Subtitling](https://mlsanity.com/paper/2209.13192/) (2022)
- [Hearing to Translate: The Effectiveness of Speech Modality Integration into LLMs](https://mlsanity.com/paper/2512.16378/) (2025)
- [ON-TRAC Consortium Systems for the IWSLT 2022 Dialect and Low-resource Speech Translation Tasks](https://mlsanity.com/paper/2205.01987/) (2022)
- [SegAugment: Maximizing the Utility of Speech Translation Data with Segmentation-based Augmentations](https://mlsanity.com/paper/2212.09699/) (2022)
- [Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023](https://mlsanity.com/paper/2309.15554/) (2023)
- [Efficient Transformer for Direct Speech Translation](https://mlsanity.com/paper/2107.03069/) (2021)
- [Joint Speech Translation and Named Entity Recognition](https://mlsanity.com/paper/2210.11987/) (2022)
- [Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation](https://mlsanity.com/paper/2305.07455/) (2023)
- [Prosody in Cascade and Direct Speech-to-Text Translation: a case study on Korean Wh-Phrases](https://mlsanity.com/paper/2402.00632/) (2024)
- [Evaluating the IWSLT2023 Speech Translation Tasks: Human Annotations, Automatic Metrics, and Segmentation](https://mlsanity.com/paper/2406.03881/) (2024)
- [Label-Synchronous Neural Transducer for E2E Simultaneous Speech Translation](https://mlsanity.com/paper/2406.04541/) (2024)
- [Towards Building Large Scale Datasets and State-of-the-Art Automatic Speech Translation Systems for 14 Indian Languages](https://mlsanity.com/paper/2411.04699/) (2024)
- [Named Entity Detection and Injection for Direct Speech Translation](https://mlsanity.com/paper/2210.11981/) (2022)

## Abstract (arXiv)

Five years after the first published proofs of concept, direct approaches to speech translation (ST) are now competing with traditional cascade solutions. In light of this steady progress, can we claim that the performance gap between the two is closed? Starting from this question, we present a systematic comparison between state-of-the-art systems representative of the two paradigms. Focusing on three language directions (English-German/Italian/Spanish), we conduct automatic and manual evaluations, exploiting high-quality professional post-edits and annotations. Our multi-faceted analysis on one of the few publicly available ST benchmarks attests for the first time that: i) the gap between the two paradigms is now closed, and ii) the subtle differences observed in their behavior are not sufficient for humans neither to distinguish them nor to prefer one over the other.