Inventor · Sammamish, WA, US

Mei-Yuh Hwang

24Patents
14h-index
37Co-inventors
81Inventor score

Filing activity: Jun 28, 1996 → Dec 24, 2021

Most-cited inventions

PatentTitleAreaCited byStatus
US7676365B2 Method and apparatus for constructing and using syllable-like unit language models Physics 344 Active
US7693715B2 Generating large units of graphonemes with mutual information criterion for letter to sound conversion Physics 338 Active
US6260011A Methods and apparatus for automatically synchronizing electronic audio files with electronic text files Physics 295 Expired
US6263308A Methods and apparatus for performing speech recognition using acoustic models which are improved through an interactive process Physics 121 Expired
US6336108B1 Speech recognition with mixtures of bayesian networks Emerging Cross-Sectional Technologies 69 Expired
US5963903A Method and system for dynamically adjusted training for speech recognition Physics 63 Expired
US6076056A Speech recognition system for recognizing continuous and isolated speech Physics 56 Expired
US6141641A Dynamically configurable acoustic model for speech recognition system Physics 47 Expired
US5794197A Senone tree representation and evaluation Physics 42 Expired
US6694296B1 Method and apparatus for the recognition of spelled spoken words Physics 41 Expired
US7031918B2 Generating a task-adapted acoustic model from one or more supervised and/or unsupervised corpora Physics 29 Expired
US6973427B2 Method for adding phonetic descriptions to a speech recognition lexicon Physics 25 Expired
US8019602B2 Automatic speech recognition learning using user corrections Physics 23 Active
US7590533B2 New-word pronunciation learning using a pronunciation graph Physics 22 Active
US9613027B2 Filled translation for bootstrapping language understanding of low-resourced languages Physics 6 Active
US7006972B2 Generating a task-adapted acoustic model from one or more different corpora Physics 6 Expired
US7263487B2 Generating a task-adapted acoustic model from one or more different corpora Physics 6 Expired
US7076422B2 Modelling and processing filled pauses and noises in speech recognition Physics 5 Expired
US10176168B2 Statistical machine translation based search query spelling correction Physics 5 Active
US10867597B2 Assignment of semantic labels to a sequence of words using neural network architectures Physics 4 Active
US8280733B2 Automatic speech recognition learning using categorization and selective incorporation of user-initiated corrections Physics 3 Active
US11238842B2 Intent recognition and emotional text-to-speech learning Physics 1 Active
US11727914B2 Intent recognition and emotional text-to-speech learning Physics 0 Active
US10290299B2 Speech recognition using a foreign word grammar Physics 0 Active

Source: USPTO / EPO open patent data. Inventor disambiguation is heuristic; counts are objective bibliographic measures.