Dining Table Having Integral Dishwasher
A space-saving dishwasher, which may be installed within a counter top or table, having a dish-carrying rack that is vertically shiftable through the open top of the dishwasher for facilitating loading and unloading of the dishes.
Make the Most of PatentStorm
See this month's Top Inventors and Most Cited Patents.
Stay on top of the latest patents by subscribing to an RSS feed.
Got questions? Ask a Patent Expert!
Registered users: Manage your profile, comments and alerts.
AbstractBootstrapping of a system from one language to another often works well when the two languages share the similar acoustic space. However, when the new language has sounds that do not occur in the language from which the bootstrapping is to be done, bootstrapping does not produce good initial models and the new language data is not properly aligned to these models. The present invention provides techniques to generate context dependent labeling of the new language data using the recognition system of another language. Then, this labeled data is used to generate models for the new language phones.Other References
| InventorsAssigneeApplicationNo. 09790296 filed on 02/22/2001US Classes:704/243, Creating patterns for matching704/254, Subportions704/255, Specialized models704/277, Translation704/244, Update patterns704/9, Natural language704/256.2, Training of HMM (EPO)704/256, Markov704/238, Distance704/220Analysis by synthesisField of Search704/1, LINGUISTICS704/2, Translation machine704/8, Multilingual or national language support704/9, Natural language704/256.5, Hidden Markov (HM) network (EPO)704/256.6, State emission probability (EPO)704/256.7, Continuous density, e.g, Gaussian distribution, Lapalce (EPO)704/256.2, Training of HMM (EPO)704/256, Markov704/257, Natural language704/256.8, Discrete density, e.g., Vector Quantization preprocessor, look up tables (EPO)704/256.3, With insufficient amount of training data, e.g., state sharing, tying, deleted interpolation (EPO)704/256.4, Duration modeling in HMM, e.g., semi HMM, segmental models, transition probabilities (EPO)704/256.1, Hidden Markov Model (HMM) (EPO)704/245, Clustering704/243, Creating patterns for matching704/244, Update patterns704/254, Subportions704/255, Specialized models704/277TranslationExaminersPrimary: Edouard, Patrick N.Assistant: Wozniak, James S. Attorney, Agent or FirmUS Patent References5477451, Method and system for natural language translationIssued on: 12/19/1995 Inventor: Brown, et al.5579436, Recognition unit model training based on competing word and word string models Issued on: 11/26/1996 Inventor: Chou, et al.6085160, Language independent speech recognition Issued on: 07/04/2000 Inventor: D'hoore, et al.6092044, Pronunciation generation in speech recognition Issued on: 07/18/2000 Inventor: Baker, et al.6212500, Process for the multilingual use of a hidden markov sound model in a speech recognition system Issued on: 04/03/2001 Inventor: Kohler6324510, Method and apparatus of hierarchically organizing an acoustic model for speech recognition and adaptation of the model to unseen domains Issued on: 11/27/2001 Inventor: Waibel, et al.6581034, Phonetic distance calculation method for similarity comparison between phonetic transcriptions of foreign words Issued on: 06/17/2003 Inventor: Choi, et al.6912499Method and apparatus for training a multilingual speech model set Issued on: 06/28/2005 Inventor: Sabourin, et al. International ClassesG10L 15/06G10L 15/00 |