7 citations · 18 across the 14 of their papers we have counts for
18 papers · 1 filter
Last Translation Benchmark
Vilém Zouhar, Niyati Bafna, Mukund Choudhary +263
For scientific progress, we need benchmarks that test the limits of state-of-the-art models, and evaluation methods that inform us about failure cases. As models get stronger, stan…
Automatic Labelling of Speech Translation Errors
Dominik Macháček, Maike Züfle, Ondrej Klejch
Errors in speech translations reduce trustworthiness of Speech Translation (ST) systems and can have serious consequences. Yet currently there is no established methodology for eva…
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
Quentin Fuxa, Dominik Macháček
We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronous cascade: Qwen3-ASR with forc…
A Pocket Offline Model for Simultaneous Speech Translation as CUNI Submission to IWSLT 2026
Aziz Sharipov Ortega, Dominik Macháček
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…
Corpus of Cross-lingual Dialogues with Minutes and Detection of Misunderstandings
Marko Čechovič, Natália Komorníková, Dominik Macháček +1
Speech processing and translation technology have the potential to facilitate meetings of individuals who do not share any common language. To evaluate automatic systems for such a…
Simultaneous Translation with Offline Speech and LLM Models in CUNI Submission to IWSLT 2025
Dominik Macháček, Peter Polák
This paper describes Charles University submission to the Simultaneous Speech Translation Task of the IWSLT 2025. We cover all four language pairs with a direct or cascade approach…
Teaching LLMs at Charles University: Assignments and Activities
Jindřich Helcl, Zdeněk Kasner, Ondřej Dušek +4
This paper presents teaching materials, particularly assignments and ideas for classroom activities, from a new course on large language models (LLMs) taught at Charles University.…
Turning Whisper into Real-Time Transcription System
Dominik Macháček, Raj Dabre, Ondřej Bojar
Whisper is one of the recent state-of-the-art multilingual speech recognition and translation models, however, it is not designed for real time transcription. In this paper, we bui…
MT Metrics Correlate with Human Ratings of Simultaneous Speech Translation
Dominik Macháček, Ondřej Bojar, Raj Dabre
There have been several meta-evaluation studies on the correlation between human ratings and offline machine translation (MT) evaluation metrics such as BLEU, chrF2, BertScore and…
Continuous Rating as Reliable Human Evaluation of Simultaneous Speech Translation
Dávid Javorský, Dominik Macháček, Ondřej Bojar
Simultaneous speech translation (SST) can be evaluated on simulated online events where human evaluators watch subtitled videos and continuously express their satisfaction by press…
The Reality of Multi-Lingual Machine Translation
Tom Kocmi, Dominik Macháček, Ondřej Bojar
Our book "The Reality of Multi-Lingual Machine Translation" discusses the benefits and perils of using more than two languages in machine translation systems. While focused on the…
Lost in Interpreting: Speech Translation from Source or Interpreter?
Dominik Macháček, Matúš Žilinec, Ondřej Bojar
Interpreters facilitate multi-lingual meetings but the affordable set of languages is often smaller than what is needed. Automatic simultaneous speech translation can extend the se…
Presenting Simultaneous Translation in Limited Space
Dominik Macháček, Ondřej Bojar
Some methods of automatic simultaneous translation of a long-form speech allow revisions of outputs, trading accuracy for low latency. Deploying these systems for users faces the p…
Promoting the Knowledge of Source Syntax in Transformer NMT Is Not Needed
Thuong-Hai Pham, Dominik Macháček, Ondřej Bojar
The utility of linguistic annotation in neural machine translation seemed to had been established in past papers. The experiments were however limited to recurrent sequence-to-sequ…
A Speech Test Set of Practice Business Presentations with Additional Relevant Texts
Dominik Macháček, Jonáš Kratochvíl, Tereza Vojtěchová +1
We present a test corpus of audio recordings and transcriptions of presentations of students' enterprises together with their slides and web-pages. The corpus is intended for evalu…
English-Czech Systems in WMT19: Document-Level Transformer
Martin Popel, Dominik Macháček, Michal Auersperger +2
We describe our NMT systems submitted to the WMT19 shared task in English-Czech news translation. Our systems are based on the Transformer model implemented in either Tensor2Tensor…
CUNI Systems for the Unsupervised News Translation Task in WMT 2019
Ivana Kvapilíková, Dominik Macháček, Ondřej Bojar
In this paper we describe the CUNI translation system used for the unsupervised news shared task of the ACL 2019 Fourth Conference on Machine Translation (WMT19). We follow the str…
Morphological and Language-Agnostic Word Segmentation for NMT
Dominik Macháček, Jonáš Vidra, Ondřej Bojar
The state of the art of handling rich morphology in neural machine translation (NMT) is to break word forms into subword units, so that the overall vocabulary size of these units f…