Abstract: A real-time speech-based learning/training system distributed between client and server, and incorporating speech recognition and linguistic processing for recognizing a spoken question and to provide an answer to the student in a learning or training environment implemented on an intranet or over the Internet, is disclosed. The system accepts the student's question in the form of speech at his or her computer, PDA or workstation where minimal processing extracts a sufficient number of acoustic speech vectors representing the utterance. The system as implemented accepts environmental variables such as course, chapter, section as selected by the user so that the search time, accuracy and response time for the question can be optimized. A minimum set of acoustic vectors extracted at the client are then sent via a communications channel to the server where additional acoustic vectors are derived.

Abstract: Methods and systems for testing speech recognition systems are disclosed in which the speech recognition device to be tested is directly monitored in accordance with a text-to-speech device. The collection of reference texts to be used by the speech recognition device is provided by a text-to-speech device preferably, in one embodiment, implemented within the same computer system. In such an embodiment, a digital audio file stored within a storage area of a computer system is generated from a reference text using a text-to-speech device. The digital audio file is later read using a speech recognition device to generate a decoded (or recognized) text representative of the reference text. The reference text and the decoded text are compared in an alignment operation and an error report representative of the recognition rate of the speech recognition device is finally generated.

Abstract: A lossless decoding method that restores losslessly compression encoded audio data on a real-time basis. The encoded audio data is divided into first data having a data amount exceeding the maximum bitrate and second data having a data amount less than the maximum bitrate, where the first data is divided into third data being the encoded audio data having a data amount of the maximum bitrate and fourth data being the encoded data of the portion exceeding the maximum bitrate, and where the encoded audio data is output so that the fourth data is output together with the second data. The method includes buffering the fourth data in a buffer, combining the buffered fourth data with the corresponding third data, and outputting the combined third and fourth data as restored audio data.

Abstract: A novel voice-enabled directory look-up system is disclosed. In one embodiment, an operator reads the first few characters from each of the first and last names of a mail addressee. The system captures the speech as an audio signal, which is parsed into character position segments. The system determines one or more candidate characters that might have resulted in the audio signal for each character position segment. The system then expands the list of candidate characters for at least one character position to include one or more characters that sound like the original candidate characters for that character position. The candidate characters for the respective character positions are composed into a regular expression, which is applied using an inexact string matching look-up routine to a directory of records. Records with the best matches are returned in a menu for the operator. The operator selects the desired record from the menu.

Abstract: An electronic interactive book allowing a child to learn the pronunciation of various words. The book will be provided with a permanent or impermanent display onto which a plurality of words, phrases or sentences would be provided. The electronic book includes a microphone as well as a speech recognition unit for recognizing a word that the child pronounces. A highlighting device such as a light emitting diode or a means for illuminating a particular word in a manner different than the surrounding words would be engaged when the child correctly pronounces that word.

Abstract: A speech coding algorithm interpolates groups speech frames into speech frame pairs, and quantizes each frame of the pair according to a different algorithm. The spectral amplitudes of the second frame are quantized by dividing them into two portions and quantizing one portion and then quantizing a difference between the two portions. The spectral amplitudes of the first frame of the pair are quantized by first converting to a fixed dimension, then interpolating between previous and subsequent frames, then selecting interpolated values in accordance with a mean squared error approach.

Abstract: The invention relates to a method for controlling an electronic device, in particular a mobile station in a mobile radio network. In order to allow simple and flexible control, the invention provides that a sound is varied in order to select from a plurality of predetermined options.

Abstract: Apparatus and process for searching for an area code from an exchange/area code directory and inserting an area code into a dialed telephone number. The inserted area code is based on the three digit exchange prefix of the dialed telephone number. An area code insertion module includes at least one entry comprising an association between an exchange number and an area code. A controller compares the digits corresponding to the exchange of a seven digit dialed telephone number with entries in the exchange/area code directory. The controller adds the resultant area code obtained from the exchange/area code directory together with any other special dialing digits required to dial such a telephone number before the digits of the dialed telephone number. A DTMF generator causes the completed telephone number to be presented to the telephone line and central office. The area code insertion module and/or the exchange/area code directory may be maintained at the customer premises equipment or at the central office.