Abstract: An encoder which encodes a voice in accordance with LD-CELP (Low-Delay Code Excited Linear Prediction) of the ITU-T Recommendation G.728. When a vibration wave is encoded by vector quantization, the code is secretly combined with other data. The encoder stores dividing key data kidx by which 128 types of representative vector data (waveform codes) yj; j=0, 1, . . . , 127 are labeled with 0 or 1 in order from the uppermost bit. If the bit is “0”, the vectors are quantized by using only the waveform codes yj corresponding to the bit “0” of the dividing key data kidx as the selection objects. If the bit is “1”, the vectors are quantized by using only the waveform codes yj corresponding to the bit “1” of the dividing key data kidx as the selection objects. Thus, the outputted voice code is combined with another datum bit.

Abstract: A voice-interactive docking station is provided for use with a portable computing device. The portable computing device includes at least one information management application and a corresponding database for storing the data associated with the information management application. The docking station generally includes a speech input device for receiving speech input, a speech recognizer for translating the speech input into voice command data, and an interface application for interacting with the applications residing on the portable computing device. In particular, the interface application, in response to voice command data, accesses the data associated with the information management application residing on the portable computing device. The docking station may further include a text-to-speech synthesizer for converting output data from the interface application into speech output data, and an audio system for generating audio output from the speech output data.

Abstract: Speech level measurement is particularly significant for successful echo compensation in telecommunications systems, for noise suppression in a noisy environment, for example in military vehicles, or in speech recognition and in speech coding and decoding systems. A method is indicated which permits speech levels measurement only if features of speech are recognized and interferences and speech pauses are filtered out for the measurement. To this end, speech and pause detectors and a mean value generator are utilized, the time behavior of which is largely adapted to the perception capability of the human ear. Briefly spoken vowels thus are well detected, while nasal sounds or consonants are suppressed in the case of falling levels. A speech level measuring device is indicated which provides very accurate results in a short adaptation period.

Abstract: A data processing apparatus includes an input terminal for receiving an audio signal, a 1-bit A/D converter for A/D converting the audio signal into a 1-bit bitstream signal, and a prediction unit for carrying out a prediction step on the bitstream signal so as to obtain a predicted bitstream signal. The data processing apparatus further includes a signal combination unit for combining the bitstream signal and the predicted bitstream signal so as to obtain a residue bitstream signal. A recording apparatus or a transmitter apparatus can use the data processing apparatus. The residue bitstream signal is data compressed by lossless encoding and then error encoded and channel encoded prior to transmission through a media.

Abstract: When necessary to time scale a speech signal, it is advantageous to do it under influence of a signal that measures the small-window non-stationarity of the speech signal. Three measures of stationarity are disclosed: one that is based on time domain analysis, one that is based on frequency domain analysis, and one that is based on both time and frequency domain analysis.

Abstract: An electronic device, e.g. a mobile telephone, includes speech recognition means for controlling the operation of the device in response to a voice command. The device includes a proximity sensor e.g. a capacitive, inductive, or IR-red proximity sensor, for providing a control signal indicative of whether an object is in proximity of the device, and control means for controlling the voice controlled operation of the device in response to the control signal.

Abstract: A wireless communication system that utilizes a remote voice recognition server system to translate voice input received from serviced mobile devices into a symbolic data file (e.g. alpha-numeric or control characters) that can be processed by the mobile devices. The translation process begins by establishing a voice communication channel between the serviced mobile device and the voice recognition server. A user of the mobile device then begins speaking in a fashion that may be detected by the voice recognition server system. Upon detecting the user's speech, the voice recognition server system translates the speech into a symbolic data file, which is then forwarded to the user through a separate data communication channel. The user, upon receiving the symbolic data file at the mobile device, reviews and edits the content and further utilizes the file as desired.

Abstract: A method and apparatus for identifying voice mail messages uses speaker identification to identify a voice mail message. The method preferably includes comparing the voice mail message to existing voice samples in order to determine a matching coefficient. If the matching coefficient is within an allowed range, the voice mail message is categorized as a matched voice mail message and a name indicator is coupled to the voice mail message. The apparatus includes a user interface, a processing unit, and a storage media. The user interface receives the voice mail message and allows access to the voice mail message by a voice mail recipient. The processing unit compares the voice mail message to the existing voice samples, determines the matching coefficient, and assigns the name indicator. The storage media stores the voice mail message.

Abstract: A signal processing method and apparatus is disclosed, which is capable of reproducing a coded audio signal by decoding it while shifting its pitch, and reproducing, from an original sound, a sound having a sufficiently higher pitch than the original sound with few operations and less cost for the decoder used in the signal processing apparatus, and an information serving medium for serving a program which implements the signal decoding and pitch shifting. In one embodiment, the method of providing a signal processing method for decoding a coded signal for reading, includes setting a pitch for the coded signal, decoding only a low frequency portion of the coded signal according to the set pitch, and shifting the pitch of the decoded read signal based on the set pitch.

Abstract: There is provided a synthesized sound generating apparatus and method which can achieve responsive and high-quality speech synthesis based on a real-time convolution operation. Coefficients are generated by using dynamic cutting to extract characteristic information from a first signal. A convolution operation is performed on a second signal using the generated coefficients to generate a synthesized signal. As the convolution operation, an interpolation process is performed on the coefficients to prevent a rapid change in level of the generated synthesized signal upon switching of the coefficients.

Abstract: The acoustic speech signal is decomposed into wavelets arranged in an asymmetrical tree data structure from which individual nodes may be selected to best extract local features, as needed to model specific classes of sound units. The wavelet packet transformation is smoothed through integration and compressed to apply a non-linearity prior to discrete cosine transformation. The resulting subband features such as cepstral coefficients may then be used to construct the speech recognizer's speech models. Using the local feature information extracted in this manner allows a single recognizer to be optimized for several different classes of sound units, thereby eliminating the need for parallel path recognizers.

Abstract: The invention relates to a method and an apparatus for separating processing for language understanding from an application and its functionality. The application for example contains functionality within a provided domain, whereby the domain and its functionality belongs to a speech controlled device such as a car-radio, a car-AC, a CD-player or almost any program controlled device.

Abstract: Speech recognition and natural language parsing components are used to extract the meaning of the user's spoken input. The system stores a semantic representation of an electronic activity guide, and the contents of the guide can be mapped into the grammars used by the natural language parser. Thus, when the user wishes to navigate through the complex menu structure of the electronic activity guide, he or she only needs to speak in natural language sentences. The system automatically filters the contents of the guide and supplies the user with on-screen display or synthesized speech responses to the user's request. The system allows the user to communicate in a natural way with a variety of devices communicating with the home network or home gateway.

Abstract: A method and an apparatus for automatic recognition of tone languages, employing the steps of converting the words of speech into an electrical signal, generating spectral features from the electrical signal, extracting pitch values from the electrical signal, combining said spectral features and the pitch values into acoustic feature vectors, comparing the acoustic feature vectors with prototypes of phonemes in an acoustic prototype database including prototypes of toned vowels to produce labels, and matching the labels to text using a decoder comprising a phonetic vocabulary and a language model database.

Abstract: A fuel delivery system performs a refueling operation in accordance with voice command signals audibly provided by a customer situated within a vehicle positioned for refueling. The customer generates audio signals representative of refueling transaction information, such as a request to initiate fuel dispensing activity, data indicative of the fuel type, fuel volume, purchase amount, and form of payment, and a request to terminate the refueling transaction. A microphone detects the customer voice signals and provides audio detection signals representative thereof. A speech recognition device converts the audio detection signals into corresponding fuel dispensing command signals. A controller generates fuel dispensing control signals in accordance with the fuel dispensing command signals and couples these control signals to the fuel dispenser assembly to effect operative control thereof.

Abstract: The present-invention relates to a method for the band expansion of speech for telephones, in particular for mobile telephones, by increasing the effective sampling rate of the speech signal by the insertion of additional samples and subsequent filtering of the expanded bandwidth speech signal.

Abstract: A web-based voice messaging system uses an application server, configured for executing a voice application defined by XML documents, that accesses subscriber attributes from a standardized information database server (such as LDAP), and messages from a standardized messaging server (such as IMAP). The application server, upon receiving a request from a browser serving a subscriber, accesses an IP based messaging server to obtain a stored message for the subscriber from a second party. The stored message identifies a text-based form. The application server converts the text-based form into an audible format. The application server generates an HTML document to present to the subscriber the form in audible format with audible prompts, based on the HTTP request and the text-based form. The application server then updates the text-based form based on an input from the subscriber. Thus, text-based forms can be retrieved and acted on via a telephone.

Abstract: A system and method for customizing the operating characteristics of a speech recognition system with characteristics of a user device. The user device transmits information representing the operating characteristics of itself to the speech recognition system. The speech recognition system determines the speech characteristics of the user device from this information. The speech recognition system obtains the speech characteristics relating to the device from a database and configures the speech recognition system with these characteristics.

Abstract: A network for providing a telecommunications service with automatic speech recognition to a telecommunications user, including a switch in communication with a telecommunications device associated with the telecommunications user for storing identifying information regarding a prior calling party to the telecommunications user, and for detecting a trigger specific to the service in response to a communication from the telecommunications device, and an intelligent resource server in communication with the switch for receiving from the switch the communication from the telecommunications device and a message including the identifying information, for playing an audible message for the telecommunications user in response to receiving the communication, the audible message containing the information regarding the prior calling party and prompting the telecommunications user to place an outgoing communication to the prior calling party, and for automatically recognizing a predetermined keyword spoken by the teleco

Abstract: A model is provided for formants found in human speech. Under one aspect of the invention, the model is used in formant tracking by providing probabilities that describe the likelihood that a candidate formant is actually a formant in the speech signal. Other aspects of the invention use this formant tracking to improve the model by regenerating the model based on the formants detected by the formant tracker. Still other aspects of the invention use the formant tracking to compress a speech signal by removing some of the formants from the speech signal. A further aspect of the invention uses the formant model to synthesize speech. Under this aspect of the invention, the formant model is used to identify a most likely formant track for the synthesized speech. Based on this track, a series of resonators are used to introduce the formants into the speech signal.