A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026

• URL: http://arxiv.org/abs/2606.03948v1
• Date: Tue, 02 Jun 2026 17:37:11 GMT
• Title: A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
• Abstract summary: We implement simultaneous translation capability with the offline direct speech-to-text translation model Canary.<n>We submit it to IWSLT 2026 Simultaneous Speech Translation Shared task for Czech to English and English to German and Italian.
• Score: 0.17188280334580197
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We implement simultaneous translation capability with the offline direct speech-to-text translation model Canary, using the state-of-the-art policy AlignAtt, and submit it to IWSLT 2026 Simultaneous Speech Translation Shared task for Czech to English and English to German and Italian. The strengths of our system are: (1) high translation quality, outperforming similarly sized baselines both in low- and high-latency regimes in computationally unaware simulations; (2) low computational requirements, as the model has only 1B parameters; (3) multilinguality -- support of 25 source and 25 target languages.

Related papers

• Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025 [0.0]
  This paper describes Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025.<n>We cover all four language pairs with a direct or cascade approach.<n>The backbone of our systems is the offline Whisper speech model, which we use for both translation and transcription in simultaneous mode with the state-of-the-art simultaneous policy AlignAtt.
  arXiv  Detail & Related papers  (2025-06-20T15:27:44Z)
• CMU's IWSLT 2024 Simultaneous Speech Translation System [80.15755988907506]
  This paper describes CMU's submission to the IWSLT 2024 Simultaneous Speech Translation (SST) task for translating English speech to German text in a streaming manner. Our end-to-end speech-to-text (ST) system integrates the WavLM speech encoder, a modality adapter, and the Llama2-7B-Base model as the decoder.
  arXiv  Detail & Related papers  (2024-08-14T10:44:51Z)
• NAIST Simultaneous Speech Translation System for IWSLT 2024 [18.77311658086372]
  This paper describes NAIST's submission to the simultaneous track of the IWSLT 2024 Evaluation Campaign. We develop a multilingual end-to-end speech-to-text translation model combining two pre-trained language models, HuBERT and mBART. We trained this model with two decoding policies, Local Agreement (LA) and AlignAtt. Our speech-to-speech translation method is a cascade of the above speech-to-text model and an incremental text-to-speech (TTS) module.
  arXiv  Detail & Related papers  (2024-06-30T20:41:02Z)
• How Multilingual Are Large Language Models Fine-Tuned for Translation? [13.612090779277281]
  Fine-tuning large language models (LLM) on parallel text has been shown to outperform dedicated translation systems trained in a supervised fashion on much larger amounts of parallel data. How does translation fine-tuning impact the MT capabilities of LLMs for zero-shot languages, zero-shot language pairs, and translation tasks that do not involve English? We find that translation fine-tuning improves translation quality even for zero-shot languages on average, but that the impact is uneven depending on the language pairs involved.
  arXiv  Detail & Related papers  (2024-05-30T22:08:20Z)
• Direct Models for Simultaneous Translation and Automatic Subtitling: FBK@IWSLT2023 [26.001878009713597]
  This paper describes the FBK's participation in the Simultaneous Translation and Automatic Subtitling tracks of the IWSLT 2023 Evaluation Campaign. Our submission focused on the use of direct architectures to perform both tasks. Our English-German SimulST system shows a reduced computational-aware latency compared to the one achieved by the top-ranked systems in the 2021 and 2022 rounds of the task.
  arXiv  Detail & Related papers  (2023-09-27T10:24:42Z)
• SeamlessM4T: Massively Multilingual & Multimodal Machine Translation [90.71078166159295]
  We introduce SeamlessM4T, a single model that supports speech-to-speech translation, speech-to-text translation, text-to-text translation, and automatic speech recognition for up to 100 languages. We developed the first multilingual system capable of translating from and into English for both speech and text. On FLEURS, SeamlessM4T sets a new standard for translations into multiple target languages, achieving an improvement of 20% BLEU over the previous SOTA in direct speech-to-text translation.
  arXiv  Detail & Related papers  (2023-08-22T17:44:18Z)
• NAVER LABS Europe's Multilingual Speech Translation Systems for the IWSLT 2023 Low-Resource Track [78.80683163990446]
  This paper presents NAVER LABS Europe's systems for Tamasheq-French and Quechua-Spanish speech translation in the IWSLT 2023 Low-Resource track. Our work attempts to maximize translation quality in low-resource settings using multilingual parameter-efficient solutions.
  arXiv  Detail & Related papers  (2023-06-13T13:22:30Z)
• KIT's Multilingual Speech Translation System for IWSLT 2023 [58.5152569458259]
  We describe our speech translation system for the multilingual track of IWSLT 2023. The task requires translation into 10 languages of varying amounts of resources. Our cascaded speech system substantially outperforms its end-to-end counterpart on scientific talk translation.
  arXiv  Detail & Related papers  (2023-06-08T16:13:20Z)
• Textless Speech-to-Speech Translation With Limited Parallel Data [51.3588490789084]
  PFB is a framework for training textless S2ST models that require just dozens of hours of parallel speech data. We train and evaluate our models for English-to-German, German-to-English and Marathi-to-English translation on three different domains.
  arXiv  Detail & Related papers  (2023-05-24T17:59:05Z)
• Tencent AI Lab - Shanghai Jiao Tong University Low-Resource Translation System for the WMT22 Translation Task [49.916963624249355]
  This paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation task on English$Leftrightarrow$Livonian. Our system is based on M2M100 with novel techniques that adapt it to the target language pair.
  arXiv  Detail & Related papers  (2022-10-17T04:34:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.