Zweig - PDFSEARCH.IO - Document Search Engine

Zweig
Results: 234

#	Item
71	Hidden Variable Structures for Training and Decoding with Graphical Models in ASR Geoff Zweig CLSP WS01 Talk July 6, 2001 Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2008-04-15 16:02:42 N-gram Natural language processing Science Artificial intelligence Speech recognition Computational linguistics Linguistics
72	SCARF: A Segmental Conditional Random Field Toolkit for Speech Recognition Geoffrey Zweig and Patrick Nguyen Microsoft Corporation One Microsoft Way, Redmond, WAgzweig, Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2010-05-11 19:52:41 Speech recognition Probability Markov models Statistical natural language processing Phonetics Conditional random field N-gram Language model Acoustic model Computational linguistics Linguistics Science
73	EurospeechScandinavia Extracting Caller Information from Voicemail Geoffrey Zweig, Jing Huang, Mukund Padmanabhan IBM T. J. Watson Research Center Yorktown Heights, NY 10598 Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2006-12-20 19:16:08 Science Statistical theory Caller ID Telecommunications Natural language processing Entropy Voice-mail Speech recognition Principle of maximum entropy Telephony Computational linguistics Probability and statistics
74	INTERSPEECHAnatomy of an extremely fast LVCSR decoder George Saon, Daniel Povey and Geoffrey Zweig IBM T. J. Watson Research Center, Yorktown Heights, NY, 10598 e-mail: gsaon,dpovey,gzweig @us.ibm.com Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2006-02-10 17:47:36 Viterbi decoder Viterbi algorithm Computing Graph Telecommunications engineering Decoder Error detection and correction Mathematics Speech recognition
75	Continuous Speech Recognition with a TF-IDF Acoustic Model Geoffrey Zweig, Patrick Nguyen, Jasha Droppo and Alex Acero Microsoft Research, Redmond, WA gzweig,panguyen,jdroppo, Abstract Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2010-05-11 19:55:27 Linguistics Tf*idf Speech recognition Vector space model N-gram Segment Phoneme Inverted index Search engine indexing Information science Science Information retrieval
76	A Segmental CRF Approach to Large Vocabulary Continuous Speech Recognition Geoffrey Zweig and Patrick Nguyen Microsoft Research, Redmond, WA {gzweig,panguyen}@microsoft.com Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2009-09-05 12:53:28 Computational linguistics Statistical natural language processing Graphical models Theoretical computer science Maximum-entropy Markov model Speech recognition N-gram Conditional random field Hidden Markov model Markov models Probability Statistics
77	The IBM 2006 Speech Transcription System for European Parliamentary Speeches B. Ramabhadran, O. Siohan, L. Mangu, G. Zweig M. Westphal. H. Schulz, A. Soneiro IBM T. J. Watson Research Center Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2006-11-14 13:37:44 Artificial intelligence Automatic identification and data capture Image processing Computer accessibility Speech recognition Segmentation Cluster analysis Speech synthesis Speech Translation Computational linguistics Statistics Science
78	Advances in Large Vocabulary Continuous Speech Recognition Geoffrey Zweig and Michael Picheny IBM T. J. Watson Research Center, Yorktown Heights, NY, 10598 gzweig,picheny @us.ibm.com Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2003-08-08 16:52:56 Science Probability Speech recognition Machine learning Bioinformatics Hidden Markov model Mel-frequency cepstrum N-gram Mixture model Statistics Markov models Computational linguistics
79	EUROSPEECHGENEVA Toward Domain-Independent Conversational Speech Recognition Brian Kingsbury, Lidia Mangu, George Saon, Geoffrey Zweig, Scott Axelrod, Vaibhava Goel, Karthik Visweswariah, and Michael Picheny IBM Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2006-11-22 18:46:06 Science Humanâ€“computer interaction Computer accessibility Speech recognition Mixture model Acoustic model Hidden Markov model Mel-frequency cepstrum Computational linguistics Statistics Automatic identification and data capture
80	Maximum Mutual Information Multi-phone Units in Direct Modeling Geoffrey Zweig, Patrick Nguyen Microsoft Research, Redmond, WA {gzweig,panguyen}@microsoft.com Abstract Add to Reading List Source URL: research.microsoft.com Language: English - Date: 2009-06-15 12:40:34 Statistical theory Probability and statistics State functions Philosophy of thermal and statistical physics Entropy Mutual information Principle of maximum entropy Exponentiation Function Information theory Mathematics Statistics