--- title: "Andrew Senior — author profile and papers" description: "Andrew Senior, Google DeepMind (United Kingdom): 2 papers on Elamur Research (2016–2023), h-index 55 — affiliations, topics, co-authors and who cites…" canonical: "https://research.elamur.ai/free/en/authors/andrew-senior/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/andrew-senior/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Andrew Senior # Andrew Senior Andrew Senior works on neural network models for sequential signals, with their papers here centred on [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/) and extending to the use of machine learning on historical texts. A recurring question is how general-purpose deep learning methods, built for one kind of data, can be adapted to another, whether waveforms sampled thousands of times a second or inscriptions and manuscripts in languages no longer spoken. The most cited of these works is [WaveNet: A Generative Model for Raw Audio](https://md.research.elamur.ai/free/en/papers/oord-2016-wavenet-generative-model-raw-audio/) (2016). It asks whether an autoregressive network can generate audio one sample at a time, conditioning each value on everything before it. Rather than recurrent layers, the model uses stacks of causal convolutions with dilations that widen layer by layer, which lets it take in a long stretch of context at modest cost and train in parallel. Audio values are compressed and treated as discrete classes, and additional inputs can steer what is generated. The more recent [Machine Learning for Ancient Languages: A Survey](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/) (2023) turns from audio to texts written between the earliest Mesopotamian script and the close of the first millennium CE. It sorts the literature since 2000 according to the steps scholars actually take with such sources: digitisation, restoring damaged text, attribution, linguistic analysis, textual criticism, translation and decipherment. For each step it reviews methods ranging from hand-crafted feature classifiers to convolutional and recurrent networks. Senior is currently at Google DeepMind in London. Earlier bylines list Google in Mountain View, IBM Research's Thomas J. Watson Research Center in Yorktown Heights and the University of Cambridge. Co-authors on the papers here include [Aaron van den Oord](https://md.research.elamur.ai/free/en/authors/aaron-van-den-oord/), [Heiga Zen](https://md.research.elamur.ai/free/en/authors/heiga-zen/), [Alex Graves](https://md.research.elamur.ai/free/en/authors/alex-graves/), [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/) and [Ion Androutsopoulos](https://md.research.elamur.ai/free/en/authors/ion-androutsopoulos/). 2 papers on this site · 2016–2023 current affiliation [Google DeepMind (United Kingdom)](https://md.research.elamur.ai/free/en/companies/google-deepmind/), London, United Kingdom Andrew Senior has 2 papers on this site, in 2016–2023, most of them on [Speech & spoken language](https://md.research.elamur.ai/free/en/topics/speech/); often with [Aaron van den Oord](https://md.research.elamur.ai/free/en/authors/aaron-van-den-oord/), [Alex Graves](https://md.research.elamur.ai/free/en/authors/alex-graves/), [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/). [OpenAlex](https://openalex.org/A5079708487) · [ORCID](https://orcid.org/0000-0002-2401-5691) · [**h-index 55**](https://openalex.org/authors/A5079708487) · [140 works](https://openalex.org/works?filter=author.id:A5079708487) · [92 901 citations](https://openalex.org/works?filter=author.id:A5079708487&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works on this site](https://md.research.elamur.ai/free/en/authors/andrew-senior/#papers) · [397 citations in our library](https://md.research.elamur.ai/free/en/authors/andrew-senior/cited-by/) · 1 more work in our library 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=Andrew+Senior) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Andrew+Senior) · [dblp](https://dblp.org/search?q=Andrew+Senior) · [ACL Anthology](https://aclanthology.org/search/?q=Andrew+Senior) ## Affiliations - [Google DeepMind (United Kingdom)](https://md.research.elamur.ai/free/en/companies/google-deepmind/) · London, United Kingdom —current · 2016–2026 on 20 papers - [Google (United States)](https://md.research.elamur.ai/free/en/companies/google/) · Mountain View, United States —2009–2024 on 32 papers - [Google (United Kingdom)](https://md.research.elamur.ai/free/en/companies/google-united-kingdom/) · London, United Kingdom —2024 on 2 papers - [University of Oxford](https://md.research.elamur.ai/free/en/universities/university-of-oxford/) · Oxford, United Kingdom —2016 on 2 papers - [University of Cambridge](https://md.research.elamur.ai/free/en/universities/university-of-cambridge/) · Cambridge, United Kingdom —1994–2015 on 5 papers - [IBM Research - Thomas J. Watson Research Center](https://md.research.elamur.ai/free/en/labs/ibm-research-thomas-j-watson-research-center/) · Yorktown Heights, United States —1995–2011 on 50 papers - [IBM (United States)](https://md.research.elamur.ai/free/en/companies/ibm/) · Armonk, United States —2000–2008 on 35 papers 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 [Speech & spoken language 1](https://md.research.elamur.ai/free/en/topics/speech/) ## Works by year ### 2020s [**2023** 1 paper](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/) ### 2010s [**2016** 1 paper](https://md.research.elamur.ai/free/en/papers/oord-2016-wavenet-generative-model-raw-audio/) ## Papers The most cited first (OpenAlex and our library). 1. **[WaveNet: A Generative Model for Raw Audio](https://md.research.elamur.ai/free/en/papers/oord-2016-wavenet-generative-model-raw-audio/)** *(2016 · 5 167 citations)* WaveNet investigates whether autoregressive neural networks, previously successful for images and text, can model raw audio directly, a signal with at least 16,000 values per second. 2. **[Machine Learning for Ancient Languages: A Survey](https://md.research.elamur.ai/free/en/papers/sommerschield-2023-machine-learning-ancient-languages-survey/)** *(2023 · 123 citations)* This survey maps the published research applying machine learning to texts in ancient languages. It covers any script or writing medium from the first Mesopotamian writing (about 3400 BCE) to the end of the first millennium CE, and it leaves out pre-2000 studies and work that does not use ML. The authors organize the… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 10 co-authors with a page, the most papers together first. - [Aaron van den Oord](https://md.research.elamur.ai/free/en/authors/aaron-van-den-oord/) - [Alex Graves](https://md.research.elamur.ai/free/en/authors/alex-graves/) - [Chris Dyer](https://md.research.elamur.ai/free/en/authors/chris-dyer/) - [Heiga Zen](https://md.research.elamur.ai/free/en/authors/heiga-zen/) - [Ion Androutsopoulos](https://md.research.elamur.ai/free/en/authors/ion-androutsopoulos/) - [John Pavlopoulos](https://md.research.elamur.ai/free/en/authors/john-pavlopoulos/) - [Karen Simonyan](https://md.research.elamur.ai/free/en/authors/karen-simonyan/) - [Koray Kavukcuoglu](https://md.research.elamur.ai/free/en/authors/koray-kavukcuoglu/) - [Nal Kalchbrenner](https://md.research.elamur.ai/free/en/authors/nal-kalchbrenner/) - [Oriol Vinyals](https://md.research.elamur.ai/free/en/authors/oriol-vinyals/) ## Cited by Papers of our library cite their works 397 times (of the 140 884 papers whose bibliographies we read); [37 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/andrew-senior/cited-by/).