Abstract: An interactive voice actuated control system for a testing machine such as a tensile testing machine is described. Voice commands are passed through a user-command predictor and integrated with a graphical user interface control panel to allow hands-free operation. The user-command predictor learns operator command patterns on-line and predicts the most likely next action. It assists less experienced operators by recommending the next command, and it adds robustness to the voice command interpreter by verbally asking the operator to repeat unlikely commanded actions. The voice actuated control system applies to industrial machines whose normal operation is characterized by a nonrandom series of commands.

Abstract: Method and systems to voice-enable a user interface using a voice extension module are provided. A voice extension module includes a preprocessor, a speech recognition engine, and an input handler. The voice extension module receives user interface information, such as, a hypertext markup language (HTML) document, and voice-enables the document so that a user may interact with any user interface elements using voice commands.

Abstract: A signal modification technique facilitates compact voice coding by employing a continuous, rather than piece-wise continuous, time warp contour to modify an original residual signal to match an idealized contour, avoiding edge effects caused by prior art techniques. Warping is executed using a continuous warp contour lacking spatial discontinuities which does not invert or overly distend the positions of adjacent end points in adjacent frames. The linear shift implemented by the warp contour is derived via quadratic approximation or other method, to reduce the complexity of coding to allow for practical and economical implementation. In particular, the algorithm for determining the warp contour uses only a subset of possible contours contained within a sub-range of the range of possible contours. The relative correlation strengths from these contours are modeled as points on a polynomial trace and the optimum warp contour is calculated by maximizing the modeling function.

Abstract: The generic word label series used for recognition of words uttered by unspecified speakers are stored in the vocabulary label network accumulation processing. The speech of a particular speaker is entered. Based on the input speech, the registered word label series extraction processing generates the registered word label series. The registered word label series of the particular speaker can then be registered with the vocabulary label network accumulation processing.

Abstract: An input signal enters a noise suppression system in a time domain and is converted to a frequency domain. The noise suppression system then estimates a signal to noise ratio of the frequency domain signal. Next, a signal gain is calculated based on the estimated signal to noise ratio and a voicing parameter. The voicing parameter may be determined based on the frequency domain signal or may be determined based on a signal ahead of the frequency domain signal with respect to time. In that event, the voicing parameter is fed back to the noise suppression system, for example, by a speech coder, to calculate the signal gain. After calculating the gain, the noise suppression system modifies the signal using the calculated gain to enhance the signal quality. The modified signal may further be converted from the frequency domain back to the time domain for speech coding.

Abstract: A speech-to-text conversion system. The two-way speech recognition and dialect system comprises a computer system, an attached microphone assembly, and speech-to-text conversion software. The two-way speech recognition and dialect system includes a database of dialectal characteristics and queries a user to determine their likely dialect. The system uses this determination to reduce the time for the system to reliably transcribe a user's speech into text and to anticipate dialectal word usage. In another embodiment of the invention, the two-way speech recognition and dialect system is capable of transcribing the speech of multiple speakers while distinguishing between the different speakers and identifying the text belonging to each speaker.

Abstract: A prosody matching template in the form of a tree structure stores indices which point to lookup table and template information prescribing pitch and duration values that are used to add inflection to the output of a text-to-speech synthesizer. The lookup module employs a search algorithm that explores each branch of the tree, assigning penalty scores based on whether the syllable represented by a node of the tree does or does not match the corresponding syllable of the target word. The path with the lowest penalty score is selected as the index into the prosody template table. The system will add nodes by cloning existing nodes in cases where it is not possible to find a one-to-one match between the number of syllables in the target word and the number of nodes in the tree.

Abstract: A method of dynamically formatting a speech menu construct can include a series of steps. A markup language document containing a reference to a server-side program can be provided. The server-side program can be programmed to dynamically format data using a voice-enabled markup language. A database can be accessed using the server-side program. The database can have a plurality of data items. Using the voice-enabled markup language, the selected data items can be formatted thereby creating speech menu items. The speech menu items can specify a speech menu construct resulting in a menu interface that is dynamically generated from data in data store, rather than being written by a programmer, and allows the user to “speak to the data.

Abstract: A method for detecting a transient in a discrete-time audio signal is performed completely in the time domain and includes the step of segmenting the discrete-time audio signal so as to generate consecutive segments of the same length with unfiltered discrete-time audio signals xs(T−1). The discrete-time audio signal in a current segment is subsequently filtered. Then either the energy of the filtered discrete-time audio signal in the current segment can be compared with the energy of the filtered discrete-time audio signal in a preceding segment or a current relationship between the energy of the filtered discrete-time audio signal in the current segment and the energy of the unfiltered discrete-time audio signal in the current segment can be formed and this current relationship compared with a preceding corresponding relationship. On the basis of the one and/or the other of these comparisons it is detected whether a transient is present in the discrete-time audio signal.

Abstract: A decoder for code excited LP encoded frames with both adaptive and fixed codebooks; erased frame concealment uses muted repetitive excitation, threshold-adapted bandwidth expanded repetitive synthesis filter, and jittered repetitive pitch lag.

Abstract: A speech recognition method for use in a multimodal input system comprises receiving a multimodal input comprising digitized speech as a first modality input and data in at least one further modality input. Features in the speech and in the data in at least one further modality are identified. The identified features in the speech and in the data are used in the recognition of words by comparing the identified features with states in models for the words. The models have states for the recognition of speech and for words having features in at least one further modality associated with the words, the models also have states for the recognition of events in the further modality or each further modality.

Abstract: A low-bit-rate coding technique for unvoiced segments of speech includes the steps of extracting high-time-resolution energy coefficients from a frame of speech, quantizing the energy coefficients, generating a high-time-resolution energy envelope from the quantized energy coefficients, and reconstituting a residue signal by shaping a randomly generated noise vector with quantized values of the energy envelope. The energy envelope may be generated with a linear interpolation technique. A post-processing measure may be obtained and compared with a predefined threshold to determine whether the coding algorithm is performing adequately.

Abstract: A client/server text-to-speech synthesis system and method divides the method optimally between client and server. The server stores large databases for pronunciation analysis, prosody generation, and acoustic unit selection corresponding to a normalized text, while the client performs computationally intensive decompression and concatenation of selected acoustic units to generate speech. The units are transmitted from the client to the server in a highly compressed format, with a compression method selected based on the predetermined set of potential acoustic units. This compression method allows for very high-quality and natural-sounding speech to be output at the client machine.

Abstract: Voice synthesis with improved expressivity is obtained in a voice synthesiser of source-filter type by making use of a library of source sound categories in the source module. Each source sound category corresponds to a particular morphological category and is derived from analysis of real vocal sounds, by inverse filtering so as to subtract the effect of the vocal tract. The library may be parametrical, that is, the stored data corresponds not to the inverse-filtered sounds themselves but to synthesis coefficients for resynthesising the inverse-filtered sounds using any suitable re-synthesis technique, such as the phase vocoder technique. The coefficients are derived by Short Time Fourier Transform (STFT) analysis.

Abstract: A method and an apparatus for processing a sound signal in which a useful signal and an interference signal are specified, the sound signal being transformed into the frequency domain and a change in the profile of the frequency being represented by an envelope for at least one frequency over a time. By segmenting the envelope, a maximum is obtained for each segment, the smallest maximum, weighted by a factor, being subtracted from the sound signal. It is also possible to take account of the minimum for the purpose of reducing the interference signal.

Abstract: A speech synthesizer includes a data memory having a plurality of address areas, which stores a plurality of phases in the address areas and an address designating circuit designating one of the address areas based on the phase signal. Further, a speech synthesizer includes a speech synthesizing circuit generating a speech synthesizing signal corresponding to the phase, which is stored in the designated area, a digital/analog converter transforming the speech synthesizing signal to an analog signal having amplitude, and a counter setting a period of silence. Furthermore, a speech synthesizer includes a silence-input circuit being connected between the speech synthesizing circuit and the digital/analog converter, which supplies a predetermined voltage to the digital/analog converter for the period that is set by the counter.

Abstract: A speech coding apparatus having a speech input unit for receiving input speech, a speech coding rate selector for selecting an appropriate speech coding rate according to the power of the input speech, a speech analyzer for processing the input speech to estimate a transfer function of the speaker's oral cavity, and a speech coding unit forming a synthesis filter based on the transfer function of the oral cavity. The speech coding unit also codes an excitation signal of the synthesis filter on the basis of an estimation result supplied by the speech analyzer. A gain suppressor interposed between the speech input unit and the speech coding unit suppresses the gain of a signal supplied from the speech input unit to the speech coding unit during an unvoiced period according to information from the speech coding rate selector.

Abstract: A device and a method to be used by laryngeally impaired people to improve the naturalness of their speech. An artificial sound creating mechanism which forms a simulated glottal pulse in the vocal tract is utilized. An artificial glottal pulse is compared with the natural spectrum and an inverse filter is generated to provide an output signal which would better reproduce natural sound. A digital signal processor introduces a variation of pitch based on an algorithm developed for this purpose; i.e. creating prosody. The algorithm uses primarily the relative amplitude of the speech signal and the rise and fall rates of the amplitude as a basis for setting the frequency of the speech. The invention also clarifies speech of laryngectomees by sensing the presence of consonants in the speech and appropriately amplifying them with respect to the vowel sounds.

Abstract: The systems and methods described herein allow dictation and associated routing and formatting information to be forwarded to a transcription system. The transcription system converts the information into a document. The additional information associated with the dictation is then applied to the document to ensure proper formatting, routing, or the like. The completed document is returned to the original dictator for review and proofing. Upon approval, the document is distributed via the transcription system in accordance with distribution information associated with the document.

Abstract: The concatenative speech synthesizer employs demi-syllable subword units to generate speech. The synthesizer is based on a source-filter model that uses source signals that correspond closely to the human glottal source and that uses filter parameters that correspond closely to the human vocal tract. Concatenation of the demi-syllable units is facilitated by two separate cross face techniques, one applied in the time domain in the demi-syllable source signal waveforms, and one applied in the frequency domain by interpolating the corresponding filter parameters of the concatenated demi-syllables. The dual cross fade technique results in natural sounding synthesis that avoids time-domain glitches without degrading or smearing characteristic resonances in the filter domain.