Abstract: A voice recognition system has a vehicle unit, which is a communication terminal, and a voice recognition server. The voice recognition server recognizes a voice signal received from the vehicle unit. A sound characteristic of a communication channel for providing communication between the vehicle unit and the server requires to be adjusted so that the server properly recognizes the voice signal. A test pattern signal is used for adjusting the sound characteristic. The vehicle unit adjusts the sound characteristic based on the test pattern signal. Therefore, the server does not require a large database for the sound characteristic adjustment because it is performed by the vehicle unit.

Abstract: A system and method for predicting lexical stress is disclosed comprising a plurality of stress prediction models. In an embodiment of the invention, the stress prediction models are cascaded, i.e. one after another within the prediction system. In an embodiment of the invention, the models are cascaded in order of decreasing specificity and accuracy. There is also provided a method of generating a lexical stress prediction system. In an embodiment, the method of generation includes generating a plurality of models for use in the system. In an embodiment, the models correspond to some or all of the models described above in relation to the first aspect of the invention.

Abstract: A method to automatically generate correspondence in multiple languages includes identifying format data portions and content data portions for pieces of correspondence, storing the format data portions and content data portions in a database capable of directly storing blocks of text in both single-byte and multi-byte languages, receiving a request for generation of a piece of correspondence in a multi-byte language, accessing the database to obtain the format data portion and the content data portion of the requested piece of correspondence, and automatically generating the requested piece of correspondence. Each of the format data portions of the pieces of correspondence includes a layout and a style of a corresponding piece of correspondence, and each of the content data portions includes standard text having fixed content for all instances of the corresponding piece of correspondence and variable text having content that varies for different instances of the corresponding piece of correspondence.

Abstract: An orthographic anchor for each word in a dictionary is created in an orthographic space by mapping the words and a set of letter patterns characteristic of the words into the orthographic space. In one aspect the orthographic anchors are row or column vectors resulting from a decomposition of a matrix of feature vectors created by the mapping. In another aspect, a pronunciation for an input word is modeled based on a set of candidate phoneme strings that have pronunciations close to the input word in the orthographic space.

Abstract: A method and apparatus for building a training set for an automated speech recognition-based system, which determines the statistically optimal number of frequently requested responses to automate in order to achieve a desired automation rate. The invention may be used to select the appropriate tokens and responses to train the system and to achieve a desired “phrase coverage” for all of the many different ways human beings may phrase a request that calls for one of a plurality of frequently-requested responses. The invention also determines the statistically optimal number of tokens (spoken requests) required to train a speech recognition-based system to achieve the desired phrase coverage and optimal allocation of tokens over the set of responses that are to be automated.

Abstract: A speaker of encoded speech data recorded in a semiconductor storage device in an IC recorder is to be retrieved easily. An information receiving unit 10 in a speaker retrieval apparatus 1 reads out the encoded speech data recorded in a semiconductor storage device 107 in an IC recorder 100. A speech decoding unit 12 decodes the encoded speech data. A speaker frequency detection unit 13 discriminates the speaker based on a feature of the speech waveform decoded to find the frequency of conversation (frequency of occurrence) of the speaker in a preset time interval. A speaker frequency graph displaying unit 14 displays the speaker frequency on a picture as a two-dimensional graph having time and the frequency as two axes.

Abstract: A method and system providing a statistical representation from rule-based grammar specifications. The language model is generated by obtaining a statistical representation of a rule-based language model and combining it with a statistical representation of a statistical language model for use as a final language model. The language model may be enhanced by applying smoothing and/or adapting for use as the final language model.

Abstract: The invention concerns a method of switching from one original dialog system (1), which communicates with the user using its own dedicated speech recognition and/or speech output unit (6), to a target dialog system (2), which also communicates with the user using its own dedicated speech recognition and/or speech output unit (7), whereby the language of the speech recognition and/or speech output unit (7) of the target dialog system (2) can be set. The original dialog system (1) transfers a language information parameter (P2) to the target dialog system (2), as a result of which the language which the original dialog system (1) used for communication with the user is specified. The target dialog system (2) uses this language information parameter (P2) to set the language of the speech recognition and/or speech output unit (7) for further communication with the user.

Abstract: A method and an associated apparatus for automatically creating security policies written in specific languages of specific devices based on a security policy written in natural language. A product level policy creating apparatus comprises language conversion means and a plurality of specific device script creating means. The language conversion means converts a product level policy of a first level into an interface language. The specific device script creating means creates product level policies of a second level for the corresponding specific devices. Defining this interface language is synonymous with defining an API (Application Programming Interface). Since the API is defined thus, plug-in modules for functioning as the specific device script creating means can be easily created based on the API.

Abstract: If an adaptation is made taking into consideration the noise produced in a specific operating mode of a device in a case where the noise environment changes, a decline in recognition rate is expected during operation of the device in a mode for which no adaptation is made. Accordingly, the present operating mode of the device is detected, the name of data for speech recognition corresponding to the operating mode of the device is retrieved from a table that describes data for speech recognition, the retrieved data for speech recognition corresponding to the operating mode of the device is set and speech recognition processing is executed based upon the set data.

Abstract: Copies of original sound recordings are identified by extracting features from the copy, creating a vector of those features, and comparing that vector against a database of vectors. Identification can be performed for copies of sound recordings that have been subjected to compression and other manipulation such that they are not exact replicas of the original. Computational efficiency permits many hundreds of queries to be serviced at the same time. The vectors may be less than 100 bytes, so that many millions of vectors can be stored on a portable device.

Abstract: A system for understanding entries, such as speech, develops a classifier by employing prior knowledge with which a given corpus of training entries is enlarged threefold. A rule is created for each of the labels employed in the classifier, and the created rules are applied to the given corpus to create a corpus of attachments by appending a weight of ?p(x), or 1??p(x), to labels of entries that meet, or fail to meet, respectively, conditions of the labels' rules, and to also create a corpus of non-attachments by appending a weight of 1??p(x), or ?p(x), to labels of entries that meet, or fail to meet conditions of the labels' rules.

Abstract: A media capture device has an audio input receptive of user speech relating to a media capture activity in close temporal relation to the media capture activity. A plurality of focused speech recognition lexica respectively relating to media capture activities are stored on the device, and a speech recognizer recognizes the user speech based on a selected one of the focused speech recognition lexica. A media tagger tags captured media with generated speech recognition text, and a media annotator annotates the captured media with a sample of the user speech that is suitable for input to a speech recognizer. Tagging and annotating are based on close temporal relation between receipt of the user speech and capture of the captured media. Annotations may be converted to tags during post processing, employed to edit a lexicon using letter-to-sound rules and spelled word input, or matched directly to speech to retrieve captured media.

Abstract: The present invention is directed to a method for speech-based information retrieval in Mandarin Chinese, considering a monosyllabic structure of the Chinese language, and a whole class of syllable-based indexing terms, including overlapping segments of syllables and syllable pairs separated by a few syllables. The strong discriminating capabilities of such syllable-based indexing, terms have been verified. Special approaches for better utilizing such capabilities, including fusion with the word- and character-level information and improved approaches to obtain better syllable-based features and query expressions and so on, are disclosed too.

Abstract: A process of data process for producing Chinese-style language character includes the steps of inputting alphabetical letter keys of English languages; inputting numerical keys from 0 to 9; inputting miscellaneous symbolic and functional keys; and inputting specific Chinese character keys, wherein said Chinese character keys are used for indicative purpose to differentiate the meaning of Chinese words of similar phonetic values.

Abstract: An encoding method comprising the steps of forming a difference signal which is the difference between a first channel signal and a second channel signal of an input PCM signal, encoding the difference signal and the second channel signal with a time difference, dividing a signal which has been encoded with the time difference in the unit of a predetermined number of bits, adaptively encoding the divided data in the unit of the predetermined number of bits, and arranging the adaptively encoded data in a predetermined format.

Abstract: A second evaluation value calculation circuit calculates an evaluation value from a first linear prediction coefficient, a second linear prediction coefficient stored and held, a third linear prediction coefficient read from a table in which a plurality of linear prediction coefficients are stored in advance, and a fourth linear prediction coefficient selected, stored and held among the third linear prediction coefficients read from the table in the past, while a second evaluation value minimizing circuit selects the third linear prediction coefficient with which the evaluation value is the minimum and outputs a code corresponding to the selected third linear prediction coefficient as a code decodable by a second coding and decoding system.

Abstract: Objective measurement methods and devices for predicting perceptual quality of speech signals degraded in speech processing/transporting systems have unreliable prediction results in cases where the degraded and reference signals show in between severe timbre differences. Improvement is achieved by applying a partial compensation step within in a signal processing stage using a frequency dependently clipped compensation factor for compensating power differences between the degraded and reference signals in the frequency domain. Preferably clipping values for clipping the compensation factor have larger frequency-dependency in a range of low frequencies with respect to a centre frequency of the human auditory system, than in a range of high frequencies.

Abstract: A computer-aided reading system offers assistance to a user who is reading in a non-native language, as the user needs help, without requiring the user to divert attention away from the text. In one implementation, the reading system is implemented as a reading wizard for a browser program. The reading wizard is exposed via a graphical user interface (UI) that allows the user to select a word, phrase, sentence, or other grouping of words in the non-native text. The reading wizard automatically determines whether the selected one word comprises part of a phrase; allows the user to choose whether to view a translation of a single word or a translation of a phrase that includes the single word in response to selection by the user of the single word. The multiple translations are presented in a pop-up window, in the form of a scrollable box and is scrollable, located near the selected text to minimize distraction of the user.

Abstract: Distortion artifacts preceding a signal transient in an audio signal stream processed by a transform-based low-bit-rate audio coding system employing coding blocks are reduced by detecting a transient in the audio signal stream and shifting the temporal relationship of the transient with respect to the coding blocks such that the time duration of the distortion artifacts is reduced. The audio data is time scaled in such a way that the transients are temporally repositioned prior to quantization in a transform-based low-bit-rate audio encoder so as to reduce the amount of pre-noise in the decoded audio signal. Alternatively, or in addition, in a transform-based low-bit-rate audio coding system, a transient in the audio signal stream is detected and a portion of the distortion artifacts are time compressed such that the time duration of the distortion artifacts is reduced.