摘要:
A method for inputting ideograms into a computer system includes receiving phonetic information related to a desired ideogram to be entered and forming a candidate list of possible ideograms as a function of the phonetic information received. Stroke information, comprising one or more strokes in the desired ideogram, is received in order to obtain the desired ideogram from the candidate list.
摘要:
A method and system for dynamically selecting words for training a speech recognition system. The speech recognition system models each phoneme using a hidden Markov model and represents each word as a sequence of phonemes. The training system ranks each phoneme for each frame according to the probability that the corresponding codeword will be spoken as part of the phoneme. The training system collects spoken utterances for which the corresponding word is known. The training system then aligns the codewords of each utterance with the phoneme that it is recognized to be part of. The training system then calculates an average rank for each phoneme using the aligned codewords for the aligned frames. Finally, the training system selects words for training that contain phonemes with a low rank.
摘要:
A classifier is built to rank documents of different languages found in a query based at least in part on similarity to other documents and the relevance of those other documents to the query. A joint ranking model, e.g., based upon a Boltzmann machine, is used to represent the content similarity among documents, and to help determine joint relevance probability for a set of documents. The relevant documents of one language are thus leveraged to improve the relevance estimation for documents of different languages. In one aspect, a hidden layer of units (neurons) represents clusters (corresponding to relevant topics) among the retrieved documents, with an output layer representing the relevant documents and their features, and edges representing a relationship between clusters and documents.
摘要:
A sentence is accessed and at least one query is generated based on the sentence. At least one query can be compared to text within a collection of documents, for example using a web search engine. Collocation errors in the sentence can be detected and/or corrected based on the comparison of the at least one query and the text within the collection of documents.
摘要:
Collocation errors can be automatically proofed using local and network-based corpora, including the Web. For example, according to one illustrative method, one or more collocations from a text sample are compared with a corpus such as the content of the Web. The collocations are identified for whether they are disfavored in the corpus. Indications are provided via an output device of whether the collocations are disfavored in the corpus. Additional steps may then be taken such as searching for and providing potentially proper word collocations via a user output.
摘要:
A method and apparatus for compressing query logs is provided. Multiple levels of user-specifiable compression include character-based compression, token-based compression, and subsumption. An efficient method for performing subsumption is also provided. The compressed query logs are then used to train a statistical process such as a help function for a computer operating system.
摘要:
A text generator automatically generating a text document based on the actions of an author on a user interface. To generate the text document the author activates a recording component. The recording component records the author's actions on the user interface. Based on the recorded actions, a text generation component searches a text database and identifies an entry that matches the author's recorded actions. This text is then combined to form a text document, which provides instruction or other information to a user. During the process of generating the text document, the text can be edited using an editor as desired, such as to enhance the comprehensibility of the document.
摘要:
Tone-sensitive acoustic models are generated by first generating acoustic vectors which represent the input data. The input data is separated into multiple frames and an acoustic vector is generated for each frame which represents the input data over its corresponding frame. A tone-sensitive parameter is then generated for each of the frames which indicates the tone of the input data at its corresponding frame. Tone-sensitive parameters are generated in accordance with two embodiments. First, a pitch detector may be used to calculate a pitch for each of the frames. If a pitch cannot be detected for a particular frame, then a pitch is created for that frame based on the pitch values of surrounding frames. Second, the cross covariance between the autocorrelation coefficients for each frame and its successive frame may be generated and used as the tone-sensitive parameter. Feature vectors are then created for each frame by appending the tone-sensitive parameter for a frame to the acoustic vector for the same frame. Then, using these feature vectors, acoustic models are created which represent the input data.
摘要:
A method of correcting a text in a data processing system is described. The method includes the step of locating a first incorrect character in the text. A character list of alternative characters for the first incorrect character is then shown to the user who replaces the first incorrect character with a correct character from the character list. The change of the first incorrect character is then propagated through a remainder of the text in accordance with a matching score and a language probability score of the remainder of the text with respect to the correct character to correct any subsequent incorrect character in the text.
摘要:
A speech recognition system for continuous Mandarin Chinese speech comprises a microphone, an A/D converter, a syllable recognition system, an integrated tone classifier, and a confidence score augmentor. The syllable recognition system generates N-best theories with initial confidence scores. The integrated tone classifier has a pitch estimator to estimate the pitch of the input once and a long-term tone analyzer to segment the estimated pitch according to the syllables of each of the N-best theories. The long-term tone analyzer performs long-term tonal analysis on the segmented, estimated pitch and generates a long-term tonal confidence signal. The confidence score augmentor receives the initial confidence scores and the long-term tonal confidence signals, modifies each initial confidence score according to the corresponding long-term tonal confidence signal, re-ranks the N-best theories according to the augmented confidence scores, and outputs the N-best theories.