Abstract: A corpus is provided of language usage by non-native users of the language. Characteristics of the corpus are measured and used to create a language usage classifier for indicating non-native usage of the language. Once the language usage classifier is created, a natural language input may be entered, and the characteristics thereof measured. These characteristics are then compared with the indicators of non-native usage, thereby detecting non-native usage. The evaluation of non-native usage may be used as a versatile foundation to enhance a wide variety of tools and applications dealing with user interaction in languages other than their native language.

Abstract: A system, method, and program product for processing voice data in a conversation between two persons to determine characteristic conversation patterns. The system includes: a variation calculator for calculating a variation of a speech ratio of a first speaker and a variation calculator for calculating a variation of a speech ratio of a second speaker; a difference calculator for calculating a difference data string; a smoother for generating a smoothed difference data string; and a presenter for presenting the difference between the variation of the speech ratio of the first speaker and the speech ratio of the second speaker. The method includes: calculating a variation of a speech ratio of a first speaker and a second speaker; calculating a difference data string; generating a smoothed difference data string; and grouping them according to their patterns.

Abstract: An end-pointer determines a beginning and an end of a speech segment. The end-pointer includes a voice triggering module that identifies a portion of an audio stream that has an audio speech segment. A rule module communicates with the voice triggering module. The rule module includes a plurality of rules used to analyze a part of the audio stream to detect a beginning and an end of the audio speech segment. A consonant detector detects occurrences of a high frequency consonant in the portion of the audio stream.

Abstract: A speech analysis apparatus analyzing prosodic characteristics of speech information and outputting a prosodic discrimination result includes an input unit inputting speech information, an acoustic analysis unit calculating relative pitch variation and a discrimination unit performing speech discrimination processing, in which the acoustic analysis unit calculates a current template relative pitch difference, determining whether a difference absolute value between the current template relative pitch difference and a previous template relative pitch difference is equal to or less than a predetermined threshold or not, when the value is not less than the threshold, calculating an adjacent relative pitch difference, and when the adjacent relative pitch difference is equal to or less than a previously set margin value, executing correction processing of adding or subtracting an octave of the current template relative pitch difference to calculate the relative pitch variation by applying the relative pitch differe

Abstract: Digital audio sample data are adaptively processed for interpolation based on whether the frequency at which the digital audio signal samples reverse polarity is at least equal to a predetermined threshold, the threshold being determined by their sampling frequency. If so, the digital audio signal samples are subjected to zero-order interpolation, with zero-inserting between the samples followed by lowpass filtering; if not, the samples are subjected to Lagrange (spline) interpolation processing.

Abstract: A wideband speech coding apparatus which causes an input speech signal to be represented by spectrum parameters and an excitation signal. The apparatus includes a coding unit configured to select a plurality of pulses from given pulse position candidates, and to code the excitation signal with the selected pulses; an identification unit configured to identify whether the input speech signal is a wideband speech signal or a narrowband speech signal; and a control unit configured to control the coding unit to select a pulse position candidate having a time resolution which is set in advance in accordance with the wideband speech signal, when the identification unit identifies that the input speech signal is the wideband speech signal, and to control the coding unit to lower the time resolution of the pulse position candidate, when the identification unit identifies that the input speech signal is the narrowband speech signal.

Abstract: The present invention is disclosed a voice signal encoding/decoding methods. It is judged whether the time-point at which the voices signal is about to be encoded is one of the synchronous time parameters in the steps of voice signal encoding. If yes, output an output port code to activate a task; otherwise, then output a voice signal coded value that corresponds to the encoded voice signal at the same time. Moreover, it is judged whether the time-point at which the voice signal coded value being about to be decoded corresponds to the voice signal is one of the synchronous time parameters. If yes, output the output port code to the output port to activate a task; if not, then output a voice subsignal that corresponds to the decoded voice signal coded value at the time-point.

Abstract: An audio decoding device performs frame loss compensation capable of obtaining a decoded audio which is natural for ears with little noise. The audio decoding device includes a non-cyclic pulse waveform detection unit for detecting a non-cyclic pulse waveform section in a n?1-th frame, which is repeatedly used with a pitch cycle in the n-th frame upon compensation of loss of the n-th frame. The audio coding device also includes a non-cyclic pulse waveform suppression unit for suppressing a non-cyclic pulse waveform by replacing an audio source signal existing in the non-cyclic pulse waveform section in the n?1-th frame by a noise signal. The audio coding device further includes a synthesis filter for using a linear prediction coefficient decoded by an LPC decoding unit to perform synthesis by a synthesis filter by using the audio source signal of the n?1-th frame from the non-cyclic pulse waveform suppression unit as a drive audio source, thereby obtaining the decoded audio signal of the n-th frame.

Abstract: A speech decoding method which generates an excitation signal and a synthesis filter from coded data and which obtains a speech signal based on the excitation signal and the synthesis filter. The method includes acquiring identification information used for determining whether the speech signal to be decoded is a narrowband signal or a wideband signal; and modifying the excitation signal based on the identification information by controlling strength or presence of emphasis of pitch periodicity with respect to the excitation signal generated from the coded data, so as to generate the speech signal by use of the modified excitation signal and the synthesis filter.

Abstract: A method of managing systems in a managed network can include storing configuration information corresponding to at least one managed system and automatically generating a grammar and a speech dialog for each managed system using the configuration information. User speech selecting a managed system can be received over a telephone call. The user speech can be recognized to identify the selected managed system. A grammar and speech dialog for the selected managed system can be loaded. Accordingly, the user can interact with one or more managed systems using the speech dialog. The user speech can be processed using the grammar.

Abstract: Techniques for recognizing a personality trait associated with a user. Input from the user is analyzed to determine a number of words, including a number of compound words. The personality trait associated with the user is determined based, at least in part, on the number of compound words exceeding a threshold.

Abstract: Methods, apparatus, and computer program products are described for invoking tapered prompts in a multimodal application implemented with a multimodal browser and a multimodal application operating on a multimodal device supporting multiple modes of user interaction with the multimodal application, the modes of user interaction including a voice mode and one or more non-voice modes. Embodiments include identifying, by a multimodal browser, a prompt element in a multimodal application; identifying, by the multimodal browser, one or more attributes associated with the prompt element; and playing a speech prompt according to the one or more attributes associated with the prompt element.

Abstract: A method of pre-processing an audio signal transmitted to a user terminal via a communication network and an apparatus using the method are provided. The method of pre-processing the audio signal may prevent deterioration of a sound quality of the audio signal transmitted to the user terminal by pre-processing the audio signal, and by enabling a codec module, encoding the audio signal, to determine the audio signal as a speech signal. The method of pre-processing may include encoding the audio signal using a speech codec and decoding the encoded audio signal using the speech codec. A codec module, transmitting the decoded audio signal to the user terminal via the communication network, may determine whether a speech interval or a speechless interval with respect to at least one frame is included in the audio signal and transmit at least one parameter with respect to the at least one frame as a result of the determination.

Abstract: A method and apparatus are proposed for automatically recognizing observed audio data. An observation vector is created of audio features extracted from the observed audio data and the observed audio data is recognized from the observation vector. The audio features include features are selected from a group of 3 types of features obtained from the observed audio data: (i) ICA features obtained by processing the observed audio data, (ii) first MFCC features obtained by removing a logarithm step from the conventional MFCC process, or (iii) second MFCC features obtained by applying the ICA process to results of a mel scale filter bank.

Abstract: Characteristic features are extracted from an audio sample based on its acoustic content. The features can be coded as fingerprints, which can be used to identify the audio from a fingerprints database. The features can also be used as parameters to separate the audio into different categories.

Abstract: Mechanisms are provided for utilizing a voiceprint to authorize a user to perform an operation restricted to authorized users. A voiceprint is stored in an audio attribute file and is associated with a user. Based on a comparison of this voiceprint and an utterance provided by the user, an identification of the user is accomplished. If the utterance matches the voiceprint, the user is permitted to access services or perform operations. The audio attribute file may be transmitted from one virtual environment to another based on the detected movement of the user's avatar between virtual environments. As such, the recipient computing device may use the audio attribute file to identify the user in the new virtual environment.

Abstract: A personality-based theme may be provided to a device. An application program may query a personality resource file for a prompt corresponding to a personality. Then the prompt may be received at a text to speech synthesis engine. Next, the speech synthesis engine may query a personality voice font and recorded phrases database for a voice font corresponding to the personality and may alter the prompt text to conform with the grammatical style of the personality. Then the speech synthesis engine may apply the voice font to the prompt, which is then produced at an output device.

Abstract: A system capable of separating sound source signals with high precision while improving a convergence rate and convergence precision. A process of updating a current separation matrix Wk to a next separation matrix Wk+1 such that a next value J(Wk+1) of a cost function is closer to a minimum value J(W0) than a current value J(Wk) is iteratively performed. An update amount ?Wk of the separation matrix is increased as the current value J(Wk) of the cost function is increased and is decreased as a current gradient ?J(Wk)/?W of the cost function is rapid. On the basis of input signals x from a plurality of microphones Mi and an optimal separation matrix W0, it is possible to separate sound source signals y(=W0·x) with high precision while improving a convergence rate and convergence precision.

Abstract: A dynamic normalization factor for a current frame of a signal is determined to reduce loss in precision for low-level signals. The normalization factor depends on an amplitude of the current frame of the signal. The normalization factor also depends on values of filter states after one or more operations were performed on a previous frame of a normalized signal and on the normalization factor for the previous frame. The current frame of the signal is normalized based on the normalization factor that is determined. The states' normalization factor may be adjusted based on the normalization factor that is determined.

Abstract: A text-to-speech system adapted to operate on text in a first language including sections in a second language, includes a grapheme/phoneme transcriptor for converting the sections in the second language into phonemes of the second language; a mapping module configured for mapping at least part of the phonemes of the second language onto sets of phonemes of the first language; and a speech-synthesis module adapted to be fed with a resulting stream of phonemes including the sets of phonemes of the first language resulting from mapping and the stream of phonemes of the first language representative of the text, and to generate a speech signal from the resulting stream of phonemes.