Abstract: An apparatus for processing an audio signal to obtain control information for a speech enhancement filter has a feature extractor for extracting at least one feature per frequency band of a plurality of frequency bands of a short-time spectral representation of a plurality of short-time spectral representations, where the at least one feature represents a spectral shape of the short-time spectral representation in the frequency band. The apparatus additionally has a feature combiner for combining the at least one feature for each frequency band using combination parameters to obtain the control information for the speech enhancement filter for a time portion of the audio signal. The feature combiner can use a neural network regression method, which is based on combination parameters determined in a training phase for the neural network.

Abstract: An audio coding system in which a plurality of quantization methods are selectable for application to components of a streamed audio signal to achieve a target frame size that is determined by comparing an achieved bit rate against a target bit rate. Based on the target frame size, the system calculates a bit allocation for signal components and compares the bit allocation to the dynamic range of the signal components. Depending on the outcome of the comparison, the system may select to quantize or not quantize a signal component. The system employs lossless coding techniques, but is capable of introducing lossy coding by quantization in order to meet the target bit rate.

Abstract: In one implementation, a computer-implemented method includes receiving, at a mobile computing device, ambiguous user input that indicates more than one of a plurality of commands; and determining a current context associated with the mobile computing device that indicates where the mobile computing device is currently located. The method can further include disambiguating the ambiguous user input by selecting a command from the plurality of commands based on the current context associated with the mobile computing device; and causing output associated with performance of the selected command to be provided by the mobile computing device.

Abstract: The present invention relates to a method for speaker recognition, comprising the steps of obtaining and storing speaker information for at least one target speaker; obtaining a plurality of speech samples from a plurality of telephone calls from at least one unknown speaker; classifying the speech samples according to the at least one unknown speaker thereby providing speaker-dependent classes of speech samples; extracting speaker information for the speech samples of each of the speaker-dependent classes of speech samples; combining the extracted speaker information for each of the speaker-dependent classes of speech samples; comparing the combined extracted speaker information for each of the speaker-dependent classes of speech samples with the stored speaker information for the at least one target speaker to obtain at least one comparison result; and determining whether one of the at least one unknown speakers is identical with the at least one target speaker based on the at least one comparison result.

Abstract: In a method of improving perceived loudness and sharpness of a reconstructed speech signal delimited by a predetermined bandwidth, performing the steps of providing (S10) the speech signal, and separating (S20) the provided signal into at least a first and a second signal portion. Subsequently, adapting (S30) the first signal portion to emphasize at least a predetermined frequency or frequency interval within the first bandwidth portion. Finally, reconstructing (S40) the second signal portion based on at least the first signal portion, and combining (S50) the adapted first signal portion and the reconstructed second signal portion to provide a reconstructed speech signal with an overall improved perceived loudness and sharpness.

Abstract: MDCT or FFT-based audio coding algorithms often have the problem named here spectral pre-echoes when coding an energy attack signal. This invention presents several possibilities to avoid the spectral pre-echoes existing in decoded signal segment before the energy attack point. The spectral envelope before the attack point can be improved by performing spectrum smoothing, replacing the segment of having spectral pre-echoes or filtering the segment with a combined filter obtained by doing LPC analysis.

Abstract: A method, computer readable medium and apparatus for detecting a sentiment for a short message are disclosed. For example, the method receives the short message, and obtains an abstraction of the short message. The method then determines the sentiment of the short message based upon the abstraction.

Abstract: Methods and devices for generating an action item summary are described. In one example embodiment, the present application describes a processor-implemented method. The method includes: receiving a request for creation of an action item, the action item comprising a record of a proposed future action; obtaining context information associated with the action item; storing the action item and context information; and generating a sentence describing the action item based on the context information associated with the action item.

Abstract: In view of the foregoing, an improved handheld electronic device includes a keypad in the form of a reduced QWERTY keyboard and is enabled with disambiguation software. As a user enters keystrokes, the device provides output in the form of a default output and a number of variants from which a user can choose. The output is based largely upon the frequency, i.e., the likelihood that a user intended a particular output, but various features of the device provide additional variants that are not based solely on frequency and rather are provided by various logic structures resident on the device. The device enables editing during text entry, and when initiating an activity session on a word such as during editing, the display outputs variants of the entire word being edited, rather than providing as variants only those parts of a word that are being edited. The device also provides a learning function that allows the disambiguation function to adapt to provide a customized experience for the user.

Abstract: For a bandwidth extension of an audio signal, in a signal spreader the audio signal is temporally spread by a spread factor greater than 1. The temporally spread audio signal is then supplied to a demicator to decimate the temporally spread version by a decimation factor matched to the spread factor. The band generated by this decimation operation is extracted and distorted, and finally combined with the audio signal to obtain a bandwidth extended audio signal. A phase vocoder in the filterbank implementation or transformation implementation may be used for signal spreading.

Abstract: An apparatus for determining a plurality of local center-of-gravity frequencies of a spectrum of an audio signal includes an offset determiner, a frequency determiner and an iteration controller. The offset determiner determines an offset frequency for each iteration start frequency of a plurality of iteration start frequencies based on the spectrum of the audio signal, wherein a number of discrete sample values of the spectrum is larger than a number of iteration start frequencies. The frequency determiner determines a new plurality of iteration start frequencies by increasing or reducing each iteration start frequency of the plurality of iteration start frequencies by the corresponding determined offset frequency. The iteration controller provides the new plurality of iteration start frequencies to the offset determiner for further iteration or provides the plurality of local center-of-gravity frequencies, if a predefined termination condition is fulfilled.

Abstract: A system and method for adapting a language model to a specific environment by receiving interactions captured the specific environment, generating a collection of documents from documents retrieved from external resources, detecting in the collection of documents terms related to the environment that are not included in an initial language model and adapting the initial language model to include the terms detected.

Abstract: A global speech user interface (GSUI) comprises an input system to receive a user's spoken command, a feedback system along with a set of feedback overlays to give the user information on the progress of his spoken requests, a set of visual cues on the television screen to help the user understand what he can say, a help system, and a model for navigation among applications. The interface is extensible to make it easy to add new applications.

Abstract: A noise filler for providing a noise-filled spectral representation of an audio signal on the basis of an input spectral representation of the audio signal has a spectral region identifier configured to identify spectral regions of the input spectral representation spaced from non-zero spectral regions of the input spectral representation by at least one intermediate spectral region, to obtain identified spectral regions, and a noise inserter configured to selectively introduce noise into the identified spectral regions to obtain the noise-filled spectral representation of the audio signal. A noise filling parameter calculator for providing a noise filling parameter on the basis of a quantized spectral representation of an audio signal has a spectral region identifier, as mentioned above, and a noise value calculator configured to selectively consider quantization errors of the identified spectral regions for a calculation of the noise filling parameter.

Abstract: A method for processing an audio signal is disclosed. The method for processing an audio signal includes frequency-transforming an audio signal to generate a frequency-spectrum, deciding a weighting per band corresponding to energy per band using the frequency spectrum, receiving a masking threshold based on a psychoacoustic model, applying the weighting to the masking threshold to generate a modified masking threshold, and quantizing the audio signal using the modified masking threshold.

Abstract: A method of operating an audio processing device to improve a user's perception of an input sound includes defining a critical frequency fcrit between a low frequency range and a high frequency range, receiving an input sound by the audio processing device, and analyzing the input sound in a number of frequency bands below and above the critical frequency. The method also includes defining a cut-off frequency fcut below the critical frequency fcrit, identifying a source frequency band above the cut-off frequency fcut, and extracting an envelope of the source band. Further, the method identifying a corresponding target band below the critical frequency fcrit, extracting a phase of the target band, and combining the envelope of the source band with the phase of the target band.

Abstract: A diagnostic tool for speech recognition applications is provided, which enables a administrator to collect multiple recorded speech sessions. The administrator can then search for various failure points common to one or more of the recorded sessions in order to get a list of all sessions that have the same failure points. The invention allows the administrator to playback the session or replay any portion of the session to see the flow of the application and the recorded utterances. The invention provides the administrator with information about how to maximize the efficiency of the application which enables the administrator to edit the application to avoid future failure points.

Abstract: The voice conversion method of a display apparatus includes: in response to the receipt of a first video frame, detecting one or more entities from the first video frame; in response to the selection of one of the detected entities, storing the selected entity; in response to the selection of one of a plurality of previously-stored voice samples, storing the selected voice sample in connection with the selected entity; and in response to the receipt of a second video frame including the selected entity, changing a voice of the selected entity based on the selected voice sample and outputting the changed voice.

Abstract: Multiple nonoverlapping languages within a single document can be identified. In one embodiment, for each of a set of candidate languages, a set of non-overlapping languages is defined. The document is analyzed under the hypothesis that the whole document is in one language and that part of the document is in one language while the rest is in a different, non-overlapping language. Language(s) of the document are identified based on comparing these competing hypotheses across a number of language pairs. In another embodiment, transitions between non-overlapping character sets are used to segment a document, and each segment is scored separately for a subset of candidate languages. Language(s) of the document are identified based on the segment scores.

Abstract: A conversation scenario editor generates/edits a conversation scenario for an automatic conversation system. The system includes a conversation device and a conversation server. The conversation device generates an input sentence through speech recognition of an utterance by a user. The conversation server determines the reply sentence based on the conversation scenario when a reply sentence to the input sentence is requested from the conversation device. The editor includes a language model generator for generating a language model to be used for the speech recognition based on the conversation scenario. According to the editor, a non-expert can generate the language model to provide an adequate conversation based on the speech recognition.