Michael Riley
164 Papers
2.4K Citations
Michael Riley is an academic researcher from Google. The author has contributed to research in topics: Language model & Computer science. The author has an hindex of 44, co-authored 126 publications. Previous affiliations of Michael Riley include Alcatel-Lucent & Nuance Communications.
Chat about Author
Papers
Weighted finite-state transducers in speech recognition
TL;DR: WFSTs provide a common and natural representation for hidden Markov models (HMMs), context-dependency, pronunciation dictionaries, grammars, and alternative recognition outputs, and general transducer operations combine these representations flexibly and efficiently.
1.1K
OpenFst: a general and efficient weighted finite-state transducer library
Cyril Allauzen,Michael Riley,Johan Schalkwyk,Wojciech Skut,Mehryar Mohri +4 more
- 16 Jul 2007
TL;DR: OpenFst as mentioned in this paper is an open-source library for weighted finite-state transducers (WFSTs), which is designed to be both very efficient in time and space and to scale to very large problems.
Speech Recognition with Weighted Finite-State Transducers
Mehryar Mohri,Fernando Pereira,Michael Riley +2 more
- 01 Jan 2008
TL;DR: General algorithms for building and optimizing transducer models are presented, including composition for combining models, weighted determinization and minimization for optimizing time and space requirements, and a weight pushing algorithm for redistributing transition weights optimally for speech recognition.
Sample Selection Bias Correction Theory
Corinna Cortes,Mehryar Mohri,Michael Riley,Afshin Rostamizadeh +3 more
- 12 Oct 2008
TL;DR: In this article, the authors present a theoretical analysis of sample selection bias correction using the concept of distributional stability, which generalizes the existing concept of point-based stability and can be used to analyze other importance weighting techniques and their effect on accuracy when using a distributionally stable algorithm.
306
Methods and Apparatus for Rapid Acoustic Unit Selection From a Large Speech Corpus
TL;DR: In this article, a method for constructing an efficient concatenation cost database is provided by synthesizing a large body of speech, identifying the acoustic unit sequential pairs generated and their respective concatenations, and storing those concatenated costs likely to occur.
245