--- title: "Alex Waibel — author profile and papers" description: "Alex Waibel, Karlsruhe Institute of Technology: 5 papers on Elamur Research (2005–2026), h-index 64 — affiliations, topics, co-authors and who cites them…" canonical: "https://research.elamur.ai/free/en/authors/alex-waibel/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/alex-waibel/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Alex Waibel # Alex Waibel Alex Waibel works on machine translation and spoken language processing, with a steady interest in systems that operate across many languages at once. Their papers here range from statistical and neural translation to speech recognition, the structuring of long transcripts, and benchmarks that test models under realistic multilingual conditions. The methods include shared neural architectures, retrieval-based selection of training data, and the construction of new datasets and evaluation resources. The most cited of these papers is [Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder](https://md.research.elamur.ai/free/en/papers/ha-2016-multilingual-neural-machine-translation-universal/) (2016). It replaces separate per-language components with a single encoder and decoder for all languages and keeps the standard attention mechanism. Each word is tagged with its language, so identical spellings in different languages stay distinct while words with related meanings can still sit near each other in a common embedding space. An earlier paper, [Adaptation of the translation model for statistical machine translation based on information retrieval](https://md.research.elamur.ai/free/en/papers/hildebrand-2005-adaptation-translation-model-statistical-machine/) (2005), addressed domain mismatch. It used each test sentence as a query to retrieve similar training pairs and pooled them into one adapted corpus. Language-model perplexity then served as a stopping rule for how much data to keep. The 2026 papers turn toward long-form and conversational speech. [Paragraph Segmentation Revisited](https://md.research.elamur.ai/free/en/papers/retkowski-2026-paragraph-segmentation-revisited-standard-task/) proposes paragraph segmentation as a standard task for making recognised transcripts readable, and it releases two benchmarks built from TED talks and YouTube videos. [MUSCAT](https://md.research.elamur.ai/free/en/papers/sinhamahapatra-2026-muscat-multilingual-scientific-conversation-benchmark/) tests recognition on bilingual discussions of scientific papers, combining code-switching, technical terms and speaker turns. A shared-task submission for IWSLT 2026 deals with following instructions over long multilingual speech inputs, supported by an augmented training corpus. Waibel is affiliated with the [Karlsruhe Institute of Technology](https://md.research.elamur.ai/free/en/universities/karlsruhe-institute-of-technology/) and [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/). Co-authors on the papers here include [Jan Niehues](https://md.research.elamur.ai/free/en/authors/jan-niehues/), [Fabian Retkowski](https://md.research.elamur.ai/free/en/authors/fabian-retkowski/), Enes Yavuz Ugan and Supriti Sinhamahapatra. The work sits mainly in multilingual NLP, machine translation, and [speech and spoken language](https://md.research.elamur.ai/free/en/topics/speech/). Alex Waibel has 5 papers in our library, in 2005–2026, most of them on [Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/), [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/); often with [Jan Niehues](https://md.research.elamur.ai/free/en/authors/jan-niehues/), [Enes Yavuz Ugan](https://md.research.elamur.ai/free/en/authors/enes-yavuz-ugan/), [Fabian Retkowski](https://md.research.elamur.ai/free/en/authors/fabian-retkowski/). 5 papers in our library · 2005–2026 [OpenAlex](https://openalex.org/A5110453805) · [**h-index 64**](https://openalex.org/authors/A5110453805) · [581 works](https://openalex.org/works?filter=author.id:A5110453805) · [16,431 citations](https://openalex.org/works?filter=author.id:A5110453805&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [📄 5 works in our library](https://md.research.elamur.ai/free/en/authors/alex-waibel/#papers) · [🔗 592 citations in our library](https://md.research.elamur.ai/free/en/authors/alex-waibel/cited-by/) · [17 more in our library without a page yet](#also) · [⭐ Paper Star rank #2627](https://md.research.elamur.ai/free/en/paper-stars/page/27/#star-2627) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Alex+Waibel) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Alex+Waibel) · [dblp](https://dblp.org/search?q=Alex+Waibel) · [ACL Anthology](https://aclanthology.org/search/?q=Alex+Waibel) ## Affiliations [🎓**Carnegie Mellon University** Pittsburgh · United States 1980–2025 · 283 papers*current*](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) · [🎓**Karlsruhe Institute of Technology** Karlsruhe · Germany 1991–2025 · 177 papers*current*](https://md.research.elamur.ai/free/en/universities/karlsruhe-institute-of-technology/) · [🎓**Nara Institute of Science and Technology** Ikoma · Japan 2012–2024 · 3 papers](https://md.research.elamur.ai/free/en/universities/nara-institute-of-science-and-technology/) · [🎓**Maastricht University** Maastricht · Netherlands 2019 · 2 papers](https://md.research.elamur.ai/free/en/universities/maastricht-university/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 3 more institutions on single bylines are not listed. ## Topics [Multilingual & cross-lingual NLP (3)](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · [Machine translation (2)](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Speech & spoken language (1)](https://md.research.elamur.ai/free/en/topics/speech/) · [Evaluation & benchmarks (1)](https://md.research.elamur.ai/free/en/topics/evaluation-benchmarks/) · [Information retrieval & search (1)](https://md.research.elamur.ai/free/en/topics/information-retrieval/) ## Works by year ### 2020s [**2026** 3 papers](https://md.research.elamur.ai/free/en/authors/alex-waibel/year/2026/) ### 2010s [**2016** 1 paper](https://md.research.elamur.ai/free/en/papers/ha-2016-multilingual-neural-machine-translation-universal/) ### 2000s [**2005** 1 paper](https://md.research.elamur.ai/free/en/papers/hildebrand-2005-adaptation-translation-model-statistical-machine/) ## Papers The most cited first (OpenAlex and our library). 1. **[Toward Multilingual Neural Machine Translation with Universal Encoder and Decoder](https://md.research.elamur.ai/free/en/papers/ha-2016-multilingual-neural-machine-translation-universal/)** *(2016 · 398 citations)* Attention-based NMT is usually trained for one language pair. Earlier multilingual extensions used several encoders or decoders and custom ways of sharing or merging attention, which adds parameters and complicates training. Ha, Niehues and Waibel propose a simpler design: a single shared encoder and a single shared… 2. **[Adaptation of the translation model for statistical machine translation based on information retrieval](https://md.research.elamur.ai/free/en/papers/hildebrand-2005-adaptation-translation-model-statistical-machine/)** *(2005 · 230 citations)* The paper tackles domain mismatch in statistical machine translation. When large out-of-domain bilingual data is merged with a small in-domain corpus, the resulting translation model may pick word senses that are wrong for the test topic. The authors treat each source-side training sentence as a document and each… 3. **[Paragraph Segmentation Revisited: Towards a Standard Task for Structuring Speech](https://md.research.elamur.ai/free/en/papers/retkowski-2026-paragraph-segmentation-revisited-standard-task/)** *(2026 · 2 citations)* ASR systems usually produce a flat stream of words, which makes long transcripts of lectures, talks or videos hard to read and reuse. 4. **[Multilingual Long-Form Speech Instruction Following: KIT's Submission to IWSLT 2026](https://md.research.elamur.ai/free/en/papers/ugan-2026-multilingual-long-form-speech-instruction/)** *(2026 · 1 citation)* This paper describes the Karlsruhe Institute of Technology's entry to the unconstrained Long and Short Instruction Following tracks at IWSLT 2026. 5. **[MUSCAT: MUltilingual, SCientific ConversATion Benchmark](https://md.research.elamur.ai/free/en/papers/sinhamahapatra-2026-muscat-multilingual-scientific-conversation-benchmark/)** *(2026 · 1 citation)* MUSCAT is a benchmark that tests whether current automatic speech recognition (ASR) systems can handle realistic multilingual dialogue. ## Also in our library 17 more works of theirs are in our library without a page here yet; they will appear as we publish them. ## Co-authors here 6 co-authors with a page, the most papers together first. - [Jan Niehues](https://md.research.elamur.ai/free/en/authors/jan-niehues/) ×3 - [Enes Yavuz Ugan](https://md.research.elamur.ai/free/en/authors/enes-yavuz-ugan/) ×2 - [Fabian Retkowski](https://md.research.elamur.ai/free/en/authors/fabian-retkowski/) ×2 - [Supriti Sinhamahapatra](https://md.research.elamur.ai/free/en/authors/supriti-sinhamahapatra/) ×2 - [Maike Züfle](https://md.research.elamur.ai/free/en/authors/maike-zufle/) - [Stephan Vogel](https://md.research.elamur.ai/free/en/authors/stephan-vogel/) ## Cited by Papers of our library cite their works 592 times (of the 140,884 papers whose bibliographies we read); [35 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/alex-waibel/cited-by/).