F
Fileno A. Alleva
Researcher at Microsoft
Publications - 32
Citations - 2791
Fileno A. Alleva is an academic researcher from Microsoft. The author has contributed to research in topics: Language model & Acoustic model. The author has an hindex of 23, co-authored 32 publications receiving 2679 citations. Previous affiliations of Fileno A. Alleva include Carnegie Mellon University.
Papers
More filters
Journal ArticleDOI
The SPHINX-II Speech Recognition System: An Overview
TL;DR: The SPHINX-II speech recognition system is reviewed and recent efforts on improved speech recognition are summarized.
Proceedings ArticleDOI
The Microsoft 2017 Conversational Speech Recognition System
TL;DR: The latest version of Microsoft's conversational speech recognition system for the Switchboard and CallHome domains is described, which adds a CNN-BLSTM acoustic model to the set of model architectures combined previously, and includes character-based and dialog session aware LSTM language models in rescoring.
Posted Content
The Microsoft 2017 Conversational Speech Recognition System
TL;DR: The 2017 version of Microsoft's conversational speech recognition system is described in this article, which adds a CNN-BLSTM acoustic model to the set of model architectures we combined previously, and includes character-based and dialog session aware LSTM language models in rescoring.
Patent
Methods and apparatus for automatically synchronizing electronic audio files with electronic text files
David Heckerman,Fileno A. Alleva,Robert L. Rounthwaite,Daniel Rosen,Mei-Yuh Hwang,Yoram Yaacovi,John L. Manferdelli +6 more
TL;DR: In this paper, a statistical language model is generated from the text data and a speech recognition operation is performed on the audio data using the generated language model and a speaker independent acoustic model.
Patent
Method and apparatus for constructing and using syllable-like unit language models
TL;DR: In this paper, a method and computer-readable medium use syllable-like units (SLUs) to decode a pronunciation into a phonetic description, which are generally larger than a single phoneme but smaller than a word.