Abstract: Methods and apparatus implementing a technique for producing an audio output customized to a listener's hearing impairment through a digital telephone. A user initially sets user parameters to represent the user's hearing spectrum. In receiving a call, the digital telephone receives an input signal. The digital telephone adjusts the input signal according to the user parameters and generates an output signal based upon the adjusted input signal.

Abstract: A text segment selection unit extracts parameters of exemplary text segment of a user's choice and a fixed form portion in the exemplary text segment from an exemplary text segment database. A text segment input unit inputs a text segment of a user's choice to e embedded to an unfixed form portion in the exemplary text segment. A text segment generation unit concatenates the input text segment to the text segment of the fixed form portion. A parameter generation unit generates a parameter from the concatenated text segment. A parameter extraction unit extracts the parameter of the unfixed form portion from the generated parameter. A parameter embedding unit concatenates the parameter of the unfixed form portion to the parameter of the fixed form portion to generate a parameter for speech synthesis. A synthesis unit generates synthesized speech from this parameter.

Abstract: A differential pulse-code modulation coder obtains an improved signal-to-noise ratio, with only a small increase in bit rate, by repetitive coding. In one aspect, the coder divides the input signal into frames, codes each frame repeatedly using different prediction coefficients or different quantizing step functions, and selects the coefficient or step function that produces the least quantization error. In another aspect, the coder repeats the coding of individual samples located in the outermost steps of the quantizing step function.

Abstract: A first CELP coding circuit receiving a signal obtained by down-sampling of an input signal by a down-sampling circuit, outputs a part of coded output to a second CELP coding circuit. The second CELP coding circuit encodes the input signal on the basis of the coded output of the first CELP coding circuit. A multiplexer outputs the coded outputs of the first and second CELP coding circuits in a form of a bit stream. A demultiplexer outputs the coded output of the first CELP coding circuit from the bit stream to a first CELP decoding circuit when a control signal is low bit rate, and extracts a part of the output of the first CELP coding circuit and the output of the second CELP coding circuit to output to a second CELP decoding circuit to output via a switch circuit when the control signal is high bit rate.

Abstract: For machine segmenting of speech, first utterances from a database of known spoken words are classified and segmented into three broad phonetic classes (BPC) voiced, unvoiced, and silence. Next, using preliminary segmentation positions as anchor points, sequence-constrained vector quantization is used for further segmentation into phoneme-like units. Finally, exact tuning to the segmented phonemes is done through Hidden-Markov Modelling and after training a diphone set is composed for further usage.

Abstract: A method and apparatus for recognizing an input identifier on the basis of a set of comparison identifiers. After a user provides the input identifier according to a first form, the present invention provides a recognized identifier based on the input identifier. The present invention then generates a plurality of comparison identifiers on the basis of the recognized identifier. The user is then prompted to provide the input identifier again, but this time according to a second form that is different than the first form. A second recognized identifier is then generated on the basis of the input identifier provided according to the second form. If a match exists between the second recognized identifier and one of the comparison identifiers, the matched comparison identifier is selected as corresponding to the input identifier.

Abstract: A method and apparatus for reducing a set of reference identifiers to a candidate subset of reference identifiers. The reference identifiers are associated in memory with a plurality of index codes. A user provides an input identifier, causing a recognizing device of the present invention to produce a recognized identifier on the basis of the input identifier. The present invention determines an index code based on the recognized identifier and on the basis of a plurality of pre-stored confusion sets of characters that group together in individual confusion sets those characters having a relatively high likelihood of being confused with each other by the recognizing device. After matching the determined index code with one of the reference index codes, the present invention determines which reference index codes are within a predetermined distance of the matched reference index code.

Abstract: The present invention provides methods and apparatuses for reducing near-far cross-talk interference between channels in a communication system. Channels of different lengths that are disposed adjacent to each other and carrying signals at the same frequencies often time create cross-talk interference in their neighboring channels. By spectrally shaping the signals carried on shorter lines the amount of cross-talk interference generated by these lines to longer lines may be significantly reduced, resulting in a better overall performance. In one embodiment of the present invention, a method of reducing the generation of near-far cross-talk interference includes spectrally shaping a signal carried on a first channel to reduce the amount of cross-talk coupling a neighboring second channel. In further embodiments, the shaping of the signal carried on the first channel is based in part on characteristics of the second and/or first channel.

Abstract: In a background noise/speech classification method, whether a digital input signal input through an input terminal is background noise or speech is decided by a background noise/speech decision section on the basis of calculated frame power and a calculated LSP coefficient which are obtained by supplying the input signal to a feature amount calculation section and estimated frame power and an estimated LSP coefficient obtained by an estimated feature amount update section. Thereafter, the estimated feature amount update section updates the estimated frame power and the estimated LSP coefficient by using the frame power and the LSP coefficient obtained by the feature amount calculation section to prepare for the next frame.

Abstract: System efficiently communicates a perceptually encoded speech spectrum signal from a transmitter to a receiver. The transmitter includes a speech analyzer which accepts a speech signal input and generates a parameterized speech signal. The transmitter also includes a vector quantizer for generating the perceptually encoded speech spectrum signal from the parameterized speech signal. The receiver decodes the perceptually encoded speech spectrum signal to produce decoded spectral parameters to further produce a synthetic speech output. The vector quantizer performs a method for partitioning a vector quantizer (VQ) codebook to produce perceptually organized sub-codebooks. The vector quantizer performs a second method for quantizing a vector based on the perceptually organized sub-codebooks. The second method identifies a vector, from one of the perceptually organized sub-codebooks, to perceptually model the speech signal input.

Abstract: In a method for detecting the state of dialling a codenumber a number already dialled digits (Nx) is counted and is compared with a defined number of digits to be dialled. If this number is reached, a timer (Tx) is started and during the runtime of the timer it is detected whether further digits are dialled. If further digits are dialled the timer is restated at every detection. If no further digit is detected, after time out of the timer a query is launched. Alternatively after launching a first query it is possible to analyse the already dialled number of digits and to define a number of digits to be dialled. If then this number is reached a timer is started and the further method is processed.

Abstract: In one embodiment of the method and apparatus for managing multiple speech applications, a common development platform and a common environment are provided. The common environment interfaces with the speech applications, receives information from an application information storage and a plurality of speech input sources, allows the speech applications to execute simultaneously and transitions from one said speech application to another seamlessly. In addition, the speech applications are developed based on the common development platform. Thus, application developers may utilize the common development platform to design and implement the speech applications independently.

Abstract: A method of training at least one new word for addition to a vocabulary of a speech recognition engine containing existing words comprises the steps of: a user uttering the at least one new word; computing respective measures between the at least one newly uttered word and at least a portion of the existing vocabulary words, the respective measures indicative of acoustic similarity between the at least one word and the at least a portion of existing words; if no measure is within the threshold range, automatically adding the at least one newly uttered word to the vocabulary; and if at least one measure is within a threshold range, refraining from automatically adding the at least one newly uttered word to the vocabulary.

Abstract: A network includes an administrative update station and an audio update station that are connected to a computer network, in particular, the World Wide Web. One or more IVR systems and one or more audio servers are likewise connected to the World Wide Web. The audio server holds the master address URL for the audio files. The IVRs access the Web in order to download updates of audio files. The audio files are administered through the Web by the administrative site and are updated through the Web by the audio update site.

Abstract: A speech coder separates input digitized speech into component parts on an interval by interval basis. The component parts include gain components, spectrum components and excitation signal components. A set of speech enhancement systems within the speech coder processes the component parts such that each component part has its own individual speech enhancement process. For example, one speech enhancement process can be applied for analyzing the spectrum components and another speech enhancement process can be used for analyzing the excitation signal components.

Abstract: A system and method for modifying a subportion of information contained in an audio, such as magnitude information, without substantially effecting the remaining information contained therein, such a phase information. An incoming audio signal is segmented into a sequence of overlapping windowed DFT representations, during an analysis step, and during a synthesis step the DFT representations are converted back to a time domain signal. Each of the DFT representations consists of a plurality of frequency components obtained during a period of time. Each of the frequency components is associated with a unique increment of the period. Subsequent to the analysis step, but before the synthesis step, the frequency components of the DFT representations are re-mapped so as to have a differing temporal relationship with respect to the increments of the period of time.

Abstract: Either or both the calling and called parties to a telephone call carried by a telecommunications network may invoke normalization of their speech to enhance intelligibility. In response to such a request, a speech normalization platform determines the manner in which the speech should be normalized. The platform does so by selecting from among a set of rules that specify the manner in which the speech should be modified, the rule that most closely corresponds with a set of parameters indicative of the party's speech. Having selected the rule, the platform then implements the rule to modify the party's speech to enhance its intelligibility.

Abstract: The generation of an audio output sound from an electronic communications device includes monitoring a level of an electrical power supply for the electrical communications device, and adjusting an audio input signal responsive to changes of the level of the electrical power supply for the electronic communications device. The adjusted audio input signal is amplified, and an output sound is generated responsive to the adjusted and amplified audio input signal. In addition, an audio output signal can be generated responsive to received sound including an echo of the output sound, an estimate of the echo of the output sound can be generated using the adjusted audio input signal and a model of an echo path of the output sound, and the echo portion of the audio output signal can be reduced using this estimate.

Abstract: A reading system includes a computer and a mass storage device including software comprising instructions for causing a computer to accept an image file generated from optically scanning an image of a document. The software convert the image file into a converted text file that includes text information, and positional information associating the text with the position of its representation in the image file. The reading system has the ability therefore to display the image representation of the scanned image on a computer monitor and permit a user to control operation of the reader by with respect to the displayed image representation of the document by using the locational information associated with the converted text file. Also described are techniques for dual highlighting spoken text and a technique for determining the nearest word to a position selected by use of mouse or other pointing device operating on the image representation as displayed on the monitor.

Abstract: Speech is received as a sequence of segments that are coded according to an LPC principle. The segments are reproduced for concatenated read-out in audio reproduction, by exciting an all-pole filter with recurrent signals in case of voiced speech and by white noise in case of unvoiced speech. In particular, the recurrent signals are globally represented as an accumulated series of periodic signals on the basis of mutually overlapping time windows. The recurrent signals are supplemented by noise for filtering through an amended LPC filter derived from the original LPC-filter by using information of pitch and formants, and of a voiced-unvoiced dichotomy. The filter is determined as depending on at least a subset of the four quantities Global Noise Scaling, Pitch Dependent Noise Scaling, Amplitude Dependent Noise Scaling, and Inter-Formant Noise Scaling.