Fil Alleva

20 papers A 1Misc 6Journal 3Unranked 10
YearRankTypeTitle / Venue / Authors
2019 Misc conf
Investigation of Sampling Techniques for Maximum Entropy Language Modeling Training.
ICASSP
Xie Chen, Jun Zhang, Tasos Anastasakos, Fil Alleva
2018 Misc conf
Multi-Microphone Neural Speech Separation for Far-Field Multi-Talker Speech Recognition.
ICASSP
Takuya Yoshioka, Hakan Erdogan, Zhuo Chen, Fil Alleva
2018 A conf
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks.
INTERSPEECH
Takuya Yoshioka, Hakan Erdogan, Zhuo Chen, Xiong Xiao, Fil Alleva
2018 J jnl
Recognizing Overlapped Speech in Meetings: A Multichannel Separation Approach Using Neural Networks.
CoRR
Takuya Yoshioka, Hakan Erdogan, Zhuo Chen, Xiong Xiao, Fil Alleva
2018 Misc conf
The Microsoft 2017 Conversational Speech Recognition System.
ICASSP
Wayne Xiong, Lingfeng Wu, Fil Alleva, Jasha Droppo, Xuedong Huang, Andreas Stolcke
2017 J jnl
The Microsoft 2017 Conversational Speech Recognition System.
CoRR
Wayne Xiong, Lingfeng Wu, Fil Alleva, Jasha Droppo, Xuedong Huang, Andreas Stolcke
1998 J jnl
Can continuous speech recognizers handle isolated speech?
Speech Commun.
Fil Alleva, Xuedong Huang, Mei-Yuh Hwang, Li Jiang
1997 — conf
Can continuous speech recognizers handle isolated speech?
EUROSPEECH
Fil Alleva, Xuedong Huang, Mei-Yuh Hwang, Li Jiang
1996 — conf
Evaluation of a language model using a clustered model backoff.
ICSLP
John Miller, Fil Alleva
1996 Misc conf
Improvements on the pronunciation prefix tree search organization.
ICASSP
Fil Alleva, Xuedong Huang, Mei-Yuh Hwang
1995 Misc conf
Microsoft Windows highly intelligent speech recognizer: Whisper.
ICASSP
Xuedong Huang, Alex Acero, Fil Alleva, Mei-Yuh Hwang, Li Jiang, Milind Mahajan
1994 — conf
Improving speech recognition performance via phone-dependent VQ codebooks and adaptive language models in SPHINX-II.
ICASSP (1)
Mei-Yuh Hwang, Ronald Rosenfeld, Eric H. Thayer, Mosur Ravishankar, Lin Lawrence Chase, Robert Weide, Xuedong Huang, Fil Alleva
1993 — conf
An improved search algorithm using incremental knowledge for continuous speech recognition.
ICASSP (2)
Fil Alleva, Xuedong Huang, Mei-Yuh Hwang
1993 — conf
Predicting unseen triphones with senones.
ICASSP (2)
Mei-Yuh Hwang, Xuedong Huang, Fil Alleva
1993 — conf
Senones, multi-pass search, and unified stochastic modeling in sphinx-II.
EUROSPEECH
Mei-Yuh Hwang, Fil Alleva, Xuedong Huang
1993 — conf
Unified stochastic engine (USE) for speech recognition.
ICASSP (2)
Xuedong Huang, M. Belin, Fil Alleva, Mei-Yuh Hwang
1992 — conf
Applying SPHINX-II to the DARPA Wall Street Journal CSR Task.
HLT
Fil Alleva, Hsiao-Wuen Hon, Xuedong Huang, Mei-Yuh Hwang, Ronald Rosenfeld, Robert Weide
1990 — conf
Improved Hidden Markov Modeling for Speaker-Independent Continuous Speech Recognition.
HLT
Xuedong Huang, Fil Alleva, Satoru Hayamizu, Hsiao-Wuen Hon, Mei-Yuh Hwang, Kai-Fu Lee
1989 — conf
Automatic New Word Acquisition: Spelling from Acoustics.
HLT (2)
Fil Alleva, Kai-Fu Lee
1986 Misc conf
A distributed system architecture for speech recognition.
ICASSP
Fil Alleva, Roberto Bisiani, S. Forin, R. Lerner