Gleb Skobeltsyn

Gleb Skobeltsyn

Gleb Skobeltsyn got his PhD from EPFL, Switzerland in Jan.2009. His research interests include: information retrieval, large-scale systems, Web search engine architectures, caching techniques, social networks, etc.
Authored Publications
Google Publications
Other Publications
Sort By
  • Title
  • Title, descending
  • Year
  • Year, descending
    Contextual prediction models for speech recognition
    Yoni Halpern
    Keith Hall
    Vlad Schogol
    Martin Baeuml
    Proceedings of Interspeech 2016
    Preview abstract We introduce an approach to biasing language models towards known contexts without requiring separate language models or explicit contextually-dependent conditioning contexts. We do so by presenting an alternative ASR objective, where we predict the acoustics and words given the contextual cue, such as the geographic location of the speaker. A simple factoring of the model results in an additional biasing term, which effectively indicates how correlated a hypothesis is with the contextual cue (e.g., given the hypothesized transcript, how likely is the user’s known location). We demonstrate that this factorization allows us to train relatively small contextual models which are effective in speech recognition. An experimental analysis shows both a perplexity reduction and a significant word error rate reductions on a voice search task when using the user’s location as a contextual cue. View details
    Workshop on large-scale distributed systems for information retrieval
    Sebastian Michel
    Wai Gen Yee
    SIGIR Forum, 43(2009), pp. 42-48
    Entity Search with NECESSITY
    Ekaterini Ioannou
    Saket Sathe
    Nicolas Bonvin
    Anshul Jain
    Srikanth Bondalapati
    Claudia Niederée
    Zoltán Miklós
    WebDB(2009)
    Query-driven indexing for scalable peer-to-peer text retrieval
    Toan Luu
    Ivana Podnar Zarko
    Martin Rajman
    Karl Aberer
    Future Generation Comp. Syst., 25(2009), pp. 89-99
    AlvisP2P: scalable peer-to-peer text retrieval in a structured P2P network
    Toan Luu
    Fabius Klemm
    Maroje Puh
    Ivana Podnar Zarko
    Martin Rajman
    Karl Aberer
    PVLDB, 1(2008), pp. 1424-1427
    ResIn: a combination of results caching and index pruning for high-performance web search engines
    Flavio Junqueira
    Vassilis Plachouras
    Ricardo A. Baeza-Yates
    SIGIR(2008), pp. 131-138
    From Web 1.0 to Web 2.0 and back -: how did your grandma use to tag?
    Sheila Kinsella
    Adriana Budura
    Sebastian Michel
    John G. Breslin
    Karl Aberer
    WIDM(2008), pp. 79-86
    Query-driven indexing for peer-to-peer text retrieval
    Toan Luu
    Karl Aberer
    Martin Rajman
    Ivana Podnar Zarko
    WWW(2007), pp. 1185-1186
    Web text retrieval with a P2P query-driven index
    Toan Luu
    Ivana Podnar Zarko
    Martin Rajman
    Karl Aberer
    SIGIR(2007), pp. 679-686
    Query-driven indexing for scalable peer-to-peer text retrieval
    Toan Luu
    Ivana Podnar Zarko
    Martin Rajman
    Karl Aberer
    Infoscale(2007), pp. 14
    Efficient Processing of XPath Queries with Structured Overlay Networks
    Manfred Hauswirth
    Karl Aberer
    OTM Conferences (2)(2005), pp. 1243-1260