摘要:
An electronic document searching system or word searching system which when given an input, expands the input as a function of acoustic similarity and/or word sequence occurrence frequency. Results of the system are alternative input words or phrases. The alternative input words or phrases are output from the system for further processing.
摘要:
A system provides assisted living messages with varying levels of detail to a person, according to proximity gradients. In one embodiment, the system involves location data. The location data associates first and second notification devices with respective first and second locations at a dwelling. A remote configuration module may enable a caregiver at a location other than the dwelling to specify multiple messages to be presented to the person at the dwelling, to assign first and second messages among the multiple messages to the first location, and to associate the first and second messages with first and second proximities, respectively, for the first location. The first notification device may automatically present the first message in response to detecting the person within the first proximity, and the second message in response to detecting the person within the second proximity. Other embodiments are described and claimed.
摘要:
A system provides assisted living messages with varying levels of detail to a person, according to proximity gradients. In one embodiment, the system involves location data. The location data associates first and second notification devices with respective first and second locations at a dwelling. A remote configuration module may enable a caregiver at a location other than the dwelling to specify multiple messages to be presented to the person at the dwelling, to assign first and second messages among the multiple messages to the first location, and to associate the first and second messages with first and second proximities, respectively, for the first location. The first notification device may automatically present the first message in response to detecting the person within the first proximity, and the second message in response to detecting the person within the second proximity. Other embodiments are described and claimed.
摘要:
A method of load-shedding in a system having a plurality of signal sources is disclosed. The method comprises the steps of: (a) for each signal source Si selected from a set of sources {S1, S2, . . . }, each source having state pi,k selected from a set of states {p1,1, p1,2, . . . , p1,N; p2,1, p2,2, . . . , p2,N; . . . }, wherein i is an integer greater than one, N is an integer not less than two and k is an integer from 1 to N: (i) obtaining fractions fi,k, wherein each 0≦fi,k
摘要翻译:公开了一种在具有多个信号源的系统中进行负载切换的方法。 该方法包括以下步骤:(a)对于从一组源(S 1,S 2,S 2)中选择的每个信号源S i, 。 。 。 },每个源具有从一组状态{p1,1,1,...,1,2]中选择的状态p i,i k。 。 。 ,p 1,N N; p2,2,1,p2,2,...。 。 。 ,p <2,N < 。 。 。 },其中i是大于1的整数,N是不小于2的整数,k是从1到N的整数:(i)获得分数f i,k,其中每个0 < = F i i,k 1是如果源S i处于状态p 1的待被丢弃的源的信号的一部分, SUB> i,k 和(ii)基于来自源SII的信号来确定信号源S i i i的相应状态p i,i i; 和(b)对于来自源的信号的丢弃分数f i,k i,在确定的状态p i i,k i中的每个源信号S i, S SUB>。
摘要:
A speech recognition system provides a subword decoder and a dictionary lookup to process a spoken input. In a first stage of processing, the subword decoder decodes the speech input based on subword units or particles and identifies hypothesized subword sequences using a particle dictionary and particle language model, but independently of a word dictionary or word vocabulary. Further stages of processing involve a particle to word graph expander and a word decoder. The particle to word graph expander expands the subword representation produced by the subword decoder into a word graph of word candidates using a word dictionary. The word decoder uses the word dictionary and a word language model to determine a best sequence of word candidates from the word graph that is most likely to match the words of the spoken input.
摘要:
A method of load-shedding in a system having a plurality of signal sources is disclosed. The method comprises the steps of: (a) for each signal source Si selected from a set of sources {S1, S2, . . . }, each source having state pi,k selected from a set of states {p1,1, p1,2, . . . , p1,N; p2,1, p2,2, . . . , p2,N; . . . }, wherein i is an integer greater than one, N is an integer not less than two and k is an integer from 1 to N: (i) obtaining fractions fi,k, wherein each 0≦fi,k
摘要:
An article is extracted from a document using a decision combiner to process a plurality of reading order alternatives. The text flow analysis generates the plurality of reading order alternatives of separate body text regions.
摘要:
A system provides assisted living messages with varying levels of detail to a person, according to proximity gradients. In one embodiment, the system involves location data. The location data associates first and second notification devices with respective first and second locations at a dwelling. A remote configuration module may enable a caregiver at a location other than the dwelling to specify multiple messages to be presented to the person at the dwelling, to assign first and second messages among the multiple messages to the first location, and to associate the first and second messages with first and second proximities, respectively, for the first location. The first notification device may automatically present the first message in response to detecting the person within the first proximity, and the second message in response to detecting the person within the second proximity. Other embodiments are described and claimed.
摘要:
A computer method and system synchronizes one streaming data signal with another data signal. A subject data signal and working data signal are received. The working data signal has predefined coordinates in a coordinate system (e.g., time origin and unit sampling rate in a time coordinate system for audio). The subject data signal and working data signal are transformed into respective common representations. An alignment process aligns the respective transformed representations by matching the transformed representation of the working data signal to that of the subject signal. A re-synchronizer element transposes the predefined coordinates of the working data signal onto the subject signal in the aligned state of the respective transformed representations. As such, the subject data signal is synchronized to the coordinate system of the working data signal.
摘要:
A computer-based detection (e.g., speech recognition) system combines a word decoder and subword decoder to detect words (or phrases) in a spoken input provided by a user into a speaker connected to the detection system. The word decoder detects words by comparing an input pattern (e.g., of hypothetical word matches) to reference patterns (e.g., words). The subword decoder compares an input pattern (e.g., hypothetical words matches based on subword or phoneme recognition) to reference patterns (e.g., words) based on a word pronunciation distance measure that indicates how close each input pattern is to matching each reference pattern. The subword decoder sorts the source set of reference patterns based on a closeness of each reference pattern to correctly matching the input pattern based on generated pattern comparisons. The word decoder and subword decoder each provide an N-best list of hypothetical matches to the spoken input. A list fusion module of the detection system selectively combines the two N-best lists to produce a final or combined N-best list. The final or combined list has a predefined number of matches.