1
Chow Yen Lu, Lee Kai Fu: Recursive finite state grammar. Apple Computer, SCHELLER James C, July 21, 1994: WO/1994/016434 (28 worldwide citation)

A method and means for performing speech recognition are described. The method and means include multiple finite state grammars. The multiple finite state grammars include at least one global finite state grammar and at least one sub-finite state grammar. Each of the multiple finite state grammars i ...


2
Hon Hsiao Wuen, Chow Yen Lu, Lee Kai Fu: Continuous mandarin chinese speech recognition system having an integrated tone classifier. Apple Computer, June 11, 1997: GB2308003-A

A speech recognition system for continuous Mandarin Chinese speech comprises a microphone, and A/D converter, a syllable recognition system, an integrated tone classifier, and a confidence score augmentor. The syllable recognition system generates N-best theories with initial confidence scores. The ...


3
Acero Alejandro, Lee Kai Fu, Chow Yen Lu: Methode arborescente pour la quantification vectorielle, A rapid tree-based method for vector quantization. Apple Computer, Apple, RICHES MCKENZIE & HERBERT, July 21, 1994: CA2151372

A fast vector quantization (VQ) method and apparatus is based on a binary tree search in which the branching decision of each node is made by a simple comparison of a pre-selected element of the candidate vector with a stored threshold resulting in a binary decision for reaching the next lower level ...


4

5
Lee Kai Fu, Chow Yen Lu, Grajski Kamil: System and method for automatic subcharacter unit and lexicon generation for handwriting recognition. Apple Computer, FERRELL John S, March 21, 1996: WO/1996/008787

A system for automatic subcharacter unit and lexicon generation for handwriting recognition comprises a processing unit, a handwriting input device, and a memory wherein a segmentation unit, a subcharacter generation unit, a lexicon unit, and a modeling unit reside. The segmentation unit generates f ...


6
Grajski Kamil A, Chow Yen Lu, Lee Kai Fu: Vector quantization with low data dimensionality for handwriting recognizer. Apple Computer, CARMICHAEL Paul D, September 8, 1995: WO/1995/024016

A handwriting signal processing front-end method and apparatus for a handwriting training and recognition system which includes non-uniform segmentation and feature extraction in combination with multiple vector quantization. In a training phase, digitized handwritting samples are partitioned into s ...


7
Acero Alejandro, Lee Kai Fu, Chow Yen Lu: A rapid tree-based method for vector quantization. Apple Computer, SCHELLER James C, July 21, 1994: WO/1994/016436

A fast vector quantization (VQ) method and apparatus is based on a binary tree search in which the branching decision of each node is made by a simple comparison of a pre-selected element of the candidate vector with a stored threshold resulting in a binary decision for reaching the next lower level ...


8
Lee Kai Fu, Chen Zheng, Han Jian: Language input architecture for converting one text form to another text form with modeless entry. Microsoft Corporation, LEE Lewis C, May 17, 2001: WO/2001/035249

A language input architecture converts input strings of phonetic text (e.g., Chinese Pinyin) to an output string of language text (e.g., Chinese Hanzi) in a manner that minimizes typographical errors and conversion errors that occur during conversion from the phonetic text to the language text. The ...


9
Lee Kai Fu, Chen Zheng, Han Jian: Language input architecture for converting one text form to another text form with tolerance to spelling, typographical, and conversion errors. Microsoft Corporation, LEE Lewis C, May 17, 2001: WO/2001/035250

A language input architecture converts input strings of phonetic text (e.g., Chinese Pinyin) to an output string of language text (e.g., Chinese Hanzi) in a manner that minimizes typographical errors and conversion errors that occur during conversion from the phonetic text to the language text. The ...


10
Hon Hsiao Wuen, Chow Yen Lu, Lee Kai Fu: Continuous mandarin chinese speech recognition system having an integrated tone classifier. Apple Computer, SUEOKA Greg T, April 11, 1996: WO/1996/010819

A speech recognition system for continuous Mandarin Chinese speech comprises a microphone, and A/D converter, a syllable recognition system, an integrated tone classifier, and a confidence score augmentor. The syllable recognition system generates N-best theories with initial confidence scores. The ...