H
Hsiao-Wuen Hon
Researcher at Apple Inc.
Publications - 9
Citations - 522
Hsiao-Wuen Hon is an academic researcher from Apple Inc.. The author has contributed to research in topics: Syllable & Frame (networking). The author has an hindex of 7, co-authored 9 publications receiving 522 citations.
Papers
More filters
Proceedings ArticleDOI
Towards large vocabulary Mandarin Chinese speech recognition
TL;DR: It is demonstrated that the sub-syllable HMM recognizer and tone classifier are able to yield state-of-the-art Mandarin Chinese syllable and tone recognition performance and a high-performance 5,000-word recognition system is developed to alleviate the homophone problem of syllable dictation.
Patent
Method and apparatus for automatically invoking a new word module for unrecognized user input
Hsiao-Wuen Hon,Yen-Lu Chow +1 more
TL;DR: In this paper, a method for reducing recognition errors in a speech recognition system that has a user interface, which instructs the user to invoke a new word acquisition module upon a predetermined condition, and that improves the recognition accuracy for poorly recognized words.
Patent
Search engine for phrase recognition based on prefix/body/suffix architecture
Yen-Lu Chow,Hsiao-Wuen Hon +1 more
TL;DR: In this article, a prefix/body/suffix language model for phrase-based search in a speech recognition system and an apparatus for constructing and/or searching through the language model is presented.
Patent
Continuous reference adaptation in a pattern recognition system
TL;DR: In this paper, a pattern recognition system which continuously adapts reference patterns to more effectively recognize input data from a given source is presented, where the input data is converted to a set or series of observed vectors and is compared to the set of Markov Models.
PatentDOI
System amd method for generating and using context dependent sub-syllable models to recognize a tonal language
Hsiao-Wuen Hon,Baosheng Yuan +1 more
TL;DR: In this article, a speech recognition system for Mandarin Chinese comprises a pre-processor (32), HMM storage (34), speech identifier (36), and speech determinator (38), which includes pseudo initials for representing glottal stops that precede syllables of lone finals.