1315 results about "Hypothesis" patented technology

A cooperative conversational voice user interface is provided. The cooperative conversational voice user interface may build upon short-term and long-term shared knowledge to generate one or more explicit and / or implicit hypotheses about an intent of a user utterance. The hypotheses may be ranked based on varying degrees of certainty, and an adaptive response may be generated for the user. Responses may be worded based on the degrees of certainty and to frame an appropriate domain for a subsequent utterance. In one implementation, misrecognitions may be tolerated, and conversational course may be corrected based on subsequent utterances and / or responses.

A system and method for speech recognition includes generating a set of likely hypotheses in recognizing speech, rescoring the likely hypotheses by using semantic content by employing semantic structured language models, and scoring parse trees to identify a best sentence according to the sentence's parse tree by employing the semantic structured language models to clarify the recognized speech.

A method and apparatus are provided for performing speech recognition using a dynamic vocabulary. Results from a preliminary speech recognition pass can be used to update or refine a language model in order to improve the accuracy of search results and to simplify subsequent recognition passes. This iterative process greatly reduces the number of alternative hypotheses produced during each speech recognition pass, as well as the time required to process subsequent passes, making the speech recognition process faster, more efficient and more accurate. The iterative process is characterized by the use of results from one or more data set queries, where the keys used to query the data set, as well as the queries themselves, are constructed in a manner that produces more effective language models for use in subsequent attempts at decoding a given speech signal.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

A method for incremental recognition of ideographic handwriting comprises in order the steps of: (1) entering in a natural stroke order at least one stroke of an ideographic character from a computer entry tablet; (2) providing the at least one stroke to an incremental character recognizer, which produces a hypothesis list of at least one candidate character; (3) displaying a hypothesis list of candidate characters containing the at least one stroke; (4) selecting a correct character from among the candidate characters on the hypothesis list if it a correct character appears thereon; (5) entering in natural stroke order at least one additional stroke of the ideographic character from the computer entry tablet if no candidate character is a correct character; (6) providing the additional stroke(s) to the incremental character recognizer, which produces an updated hypothesis list; (7) displaying the updated hypothesis list of candidate characters containing every stroke; (8) selecting a correct character from among the candidate characters on the updated hypothesis list if it a correct character appears thereon; and (9) repeating steps (5) through (8) until a correct character is selected from the updated hypothesis list.

A system and method is provided for decoding a set of bits using a plurality of hypotheses, for example, each independently tested on-the-fly. Initial bit states and associated reliability metrics may be received for the set of bits. A current hypothesis may be decoded for correcting the set of bits, wherein the current hypothesis defines different bit states and associated reliability metrics for the set of bits. If decoding the current hypothesis is not successful, a subsequently ordered hypothesis may be decoded, wherein the hypotheses are ordered such that their associated reliability metric is a monotonically non-decreasing sequence. Decoding may proceed iteratively until the current hypothesis is successful.

A technology analysis system automatically monitors information available from both publicly and privately distributed networks of information for details that are relevant to a technology hypothesis. The technology analysis system provides a technology radar that assists with determining how the technology hypothesis stands up against ongoing developments in technology. The technology analysis system also visualizes the technology hypothesis and its underlying precursor predictions using a web portal, dynamic document, or other visualization technique.

A method of determining the component words of a compound word is disclosed. The method identifies the component words, by comparing the word with a list of words found in a lexicon. If the word is not found in the lexicon the method proceeds to analyze the word on a character-by-character basis. After each character the method identifies any potential matches to the selected characters in the lexicon. If a match is found, it is added to a hypothesis trace in a lattice. Next, the method checks to see whether the remaining characters form a valid entry in the lexicon, and whether the entry is an allowed to be a final segment: All encountered component words are entered into the lattice, thus creating possibly more than one hypothesis path. Some paths may be rendered invalid, if they don't contain the required “seg1” annotation for non-final segments or had encountered an “anti-seg” bit for presumed final segment. The output can be ranked if more than one valid segmentation is found. The method can also correct spelling errors due to incorrect compounding.