Abstract: Computerized apparatus and methods for obtaining and displaying information, such as for example directions to a desired entity or organization. In one embodiment, the computerized apparatus is configured to receive user speech input and enable local performance of various tasks, such as obtaining desired information relating to entities, maps or directions, or any number of other topics. The obtained data may also, in various variants, be displayed in various formats and relative to other entities nearby.

Abstract: A speech masking apparatus includes a microphone and a speaker. The microphone can detect a human voice. The speaker can output a masking language which can include phonemes resembling human speech. At least one component of the masking language can have a pitch, a volume, a theme, and/or a phonetic content substantially matching a pitch, a volume, a theme, and/or a phonetic content of the voice.

Abstract: A system and method for remote speech recognition includes one or more customer premise equipment, a speech engine, and a communication engine. The customer premise equipment interfaces with a host from which the customer premise equipment is remotely located. The speech engine, remotely located from the host, recognizes a plurality of speech spoken by a user of the customer premise equipment and translates the speech into the language of the host. The speech engine further converts the recognized speech into one or more text data packets where the text data packets include the recognized speech as data instead of voice. The communication engine encrypts the text data packets and transmits the text data packets to the host. Transmitting data instead of voice to the host reduces the computational demands on the host. Additionally, the communication engine receives a plurality of information from the host.

Abstract: A user speech interface for interactive media guidance applications, such as television program guides, guides for audio services, guides for video-on-demand (VOD) services, guides for personal video recorders (PVRs), or other suitable guidance applications is provided. Voice commands may be received from a user and guidance activities may be performed in response to the voice commands.

Abstract: Techniques are disclosed for optimizing results output by a natural language processing system. For example, a method comprises optimizing one or more parameters of a natural language processing system so as to improve a measure of quality of an output of the natural language processing system for a first type of data processed by the natural language processing system while maintaining a given measure of quality of an output of the natural language processing system for a second type of data processed by the natural language processing system. For example, the first type of data may have a substantive complexity that is greater than that of the second type of data.

Abstract: A method includes accessing text that includes a plurality of words, tagging each of the plurality of words with one of a plurality of parts of speech (POS) tags, and creating a plurality of tokens, each token comprising one of the plurality of words and its associated POS tag. The method further includes clustering one or more of the created tokens into a chunk of tokens, the one or more tokens clustered into the chunk of tokens based on the POS tags of the one or more tokens, and forming a phrase based on the chunk of tokens, the phrase comprising the words of the one or more tokens clustered into the chunk of tokens.

Abstract: A speech enhancement method (and concomitant computer-readable medium comprising computer software encoded thereon) comprising receiving samples of a user's speech, determining mel-frequency cepstral coefficients of the samples, constructing a Gaussian mixture model of the coefficients, receiving speech from a noisy environment, determining mel-frequency cepstral coefficients of the noisy speech, estimating mel-frequency cepstral coefficients of clean speech from the mel-frequency cepstral coefficients of the noisy speech and from the Gaussian mixture model, and outputting a time-domain waveform of enhanced speech computed from the estimated mel-frequency cepstral coefficients.

Abstract: A program selection method and a display apparatus thereof are provided. The program selection method includes generating a program list including at least one program title, determining whether there is a voice input for a program selection; searching for a desired program title corresponding to the voice input for the program selection among the at least one program title in the program list, and selecting a program corresponding to the desired program title based on the searching for the desired program title.

Abstract: A mixed lossless audio compression has application to a unified lossy and lossless audio compression scheme that combines lossy and lossless audio compression within a same audio signal. The mixed lossless compression codes a transition frame between lossy and lossless coding frames to produce seamless transitions. The mixed lossless coding performs a lapped transform and inverse lapped transform to produce an appropriately windowed and folded pseudo-time domain frame, which can then be losslessly coded. The mixed lossless coding also can be applied for frames that exhibit poor lossy compression performance.

Abstract: In one embodiment, a signal processing method is disclosed. The method can perform filter processing of convoluting a tap coefficient in a first signal sequence to generate a second signal sequence. The method can subtract the second signal sequence from a third signal sequence to generate a fourth signal sequence. The third signal sequence includes an echo signal of the first signal sequence. The method can correct the tap coefficient in accordance with an amount of correction determined using a function. The function includes at least one of a first region and a second region, and has values limited. The first region is included in a negative value region of the fourth signal sequence. The second region is included in a positive value region of the fourth signal sequence.

Abstract: Architecture that uses near-end speech detection and far-end energy level detection to notify a user when a local microphone and/or speaker that the user is using, are muted. A voice activity detector is employed to detect the presence of near-end speech, sense the existing mute state of the near-end microphone, and then notify the user when the current microphone is muted. Separately or in combination therewith, received far-end voice signals are detected, the associated energy level computed, the existing mute state of the near-end audio speaker is sensed, and the user notified when the speaker is muted and/or at a reduced volume setting. These determinations enhance the user experience when the architecture is employed for communications sessions where participants connect via different communications modalities by automatically notifying the user of the audio device state, without attempting to contribute only to find that a microphone or speaker was muted.

Abstract: A method for performing packet loss or Frame Erasure Concealment (FEC) for a speech coder receives encoded frames of compressed speech information transmitted from an encoder. The method determines whether an encoded frame has been lost, corrupted in transmission, or erased, synthesizes properly received frames, and decides on an overlap-add window to use in combining a portion of the synthesized speech signal with a subsequent speech signal resulting from a received and decoded packet, where the size of the overlap-add window is based on the unavailability of packets. If it is determined that an encoded frame has been lost, corrupted in transmission, or erased, the method performed an overlap-add operation on the portion of the synthesized speech signal and the subsequent speech signal, using the decided-on overlap-add window.

Abstract: A method is disclosed for applying a multi-state barge-in acoustic model in a spoken dialogue system. The method includes receiving an audio speech input from the user during the presentation of a prompt, accumulating the audio speech input from the user, applying a non-speech component having at least two one-state Hidden Markov Models (HMMs) to the audio speech input from the user, applying a speech component having at least five three-state HMMs to the audio speech input from the user, in which each of the five three-state HMMs represents a different phonetic category, determining whether the audio speech input is a barge-in-speech input from the user, and if the audio speech input is determined to be the barge-in-speech input from the user, terminating the presentation of the prompt.

Abstract: A method applies a parametric approach to bandwidth extension but does not require training. The method computes narrowband linear predictive coefficients from a received narrowband speech signal, computes narrowband partial correlation coefficients using recursion, computes Mnb area coefficients from the partial correlation coefficient, and extracts Mwb area coefficients using interpolation. Wideband parcors are computed from the Mwb area coefficients and wideband LPCs are computed from the wideband parcors. The method further comprises synthesizing a wideband signal using the wideband LPCs and a wideband excitation signal, highpass filtering the synthesized wideband signal to produce a highband signal, and combining the highband signal with the original narrowband signal to generate a wideband signal.

Abstract: A system for accessing content maintains a set of content selections associated with a first user. The system receives first original content from a first content source associated with a first one of the content selections associated with the first user. The system applies, to the first original content, a first rule (such as a parsing rule) that is specific to the first one of the content selections, to produce first derived content. The system changes the state of at least one component of a human-machine dialogue system (such as a text-to-act engine, a dialogue manager, or an act-to-text engine) based on the first derived content. The system may apply a second rule (such as a dialogue rule) to the first derived content to produce rule output and change the state of the human-machine dialogue system based on the rule output.

Abstract: A program for generating Hidden Markov Models to be used for speech recognition with a given speech recognition system, the information storage medium storing a program, that renders a computer to function as a scheduled-to-be-used model group storage section that stores a scheduled-to-be-used model group including a plurality of Hidden Markov Models scheduled to be used by the given speech recognition system, and a filler model generation section that generates Hidden Markov Models to be used as filler models by the given speech recognition system based on all or at least a part of the Hidden Markov Model group in the scheduled-to-be-used model group.

Abstract: An apparatus and a method to encode and decode a speech signal using an encoding mode are provided. An encoding apparatus may select an encoding mode of a frame included in an input speech signal, and encode a frame having an unvoiced mode for an unvoiced speech as the selected encoding mode.

Abstract: A method for processing audio data includes determining a first common scalefactor value for representing quantized audio data in a frame. A second common scalefactor value is determined for representing the quantized audio data in the frame. A line equation common scalefactor value is determined from the first and second common scalefactor values.

Abstract: The present invention is a keyword display system that includes a speaker specifier for specify a speaker; a weight determinator for determining a weight of the specified speaker; a keyword extractor for extracting keywords from a speech of the aforementioned speaker; a keyword relation degree calculator for calculating a relation degree between the aforementioned extracted keywords, carrying out a weighting for this calculated relation degree by using the weight of the speaker having spoken the aforementioned keywords, and calculating a keyword relation degree between the keywords; and a keyword display controller for displaying a relevancy between the aforementioned extracted keywords responding to the aforementioned keyword relation degree.

Abstract: An encoding device (200) includes an MDCT unit (202) that transforms an input signal in a time domain into a frequency spectrum including a lower frequency spectrum, a BWE encoding unit (204) that generates extension data which specifies a higher frequency spectrum at a higher frequency than the lower frequency spectrum, and an encoded data stream generating unit (205) that encodes to output the lower frequency spectrum obtained by the MDCT unit (202) and the extension data obtained by the BWE encoding unit (204). The BWE encoding unit (204) generates as the extension data (i) a first parameter which specifies a lower subband which is to be copied as the higher frequency spectrum from among a plurality of the lower subbands which form the lower frequency spectrum obtained by the MDCT unit (202) and (ii) a second parameter which specifies a gain of the lower subband after being copied.