Abstract: A system and method implemented on a computing device for analyzing a digital corpus of unstructured interlocutor conversations to discover intents, goals, or both intents and goals of one or more parties to the conversations, by grouping the conversation utterances according to semantic similarity clusters; selecting the best utterance(s) that mostly likely embody a party's stated goal or intent; creates a set of candidate intent names for each cluster based upon each intent utterance in each conversation in each cluster; rates each candidate intent (or goal) for each intent name; and selects the most likely candidate intent (or goal) name for the purposes of subsequent automation of future conversations such as, but not limited to, automated electronic responses using Artificial Intelligence and machine learning.

Abstract: A system and method implemented on a computing device for analyzing a digital corpus of unstructured interlocutor conversations to discover intents, goals, or both intents and goals of one or more parties to the conversations, by grouping the conversation utterances according to semantic similarity clusters; selecting the best utterance(s) that mostly likely embody a party's stated goal or intent; creates a set of candidate intent names for each cluster based upon each intent utterance in each conversation in each cluster; rates each candidate intent (or goal) for each intent name; and selects the most likely candidate intent (or goal) name for the purposes of subsequent automation of future conversations such as, but not limited to, automated electronic responses using Artificial Intelligence and machine learning.

Abstract: In one embodiment, a method includes receiving a video file. The video file includes a corresponding audio stream. The method further includes accessing the audio stream, and generating, based on the audio stream, a representative vector. The vector has a particular number of dimensions. The method further includes accessing a label-embedding space, which has the same particular number of dimensions, and includes a number of regions that each correspond to a respective label. The method further includes determining a region of the label-embedding space that corresponds to the vector, the determined region corresponding to a particular label. The method further includes associating the particular label with the video file.

Abstract: The illustrative embodiments described herein provide systems and methods for authenticating a speaker. In one embodiment, a method includes receiving reference speech input including a reference passphrase to form a reference recording, and receiving test speech input including a test passphrase to form a test recording. The method includes determining whether the test passphrase matches the reference passphrase, and determining whether one or more voice features of the speaker of the test passphrase matches one or more voice features of the speaker of the reference passphrase. The method authenticates the speaker of the test speech input in response to determining that the reference passphrase matches the test passphrase and that one or more voice features of the speaker of the test passphrase matches one or more voice features of the speaker of the reference passphrase.

Abstract: The restoration of images by vector quantization utilizing visual patterns is disclosed. One disclosed embodiment comprises restoring detail in a transition region of an unrestored image, by first identifying the transition region and forming blurred visual pattern blocks. These blurred visual pattern blocks are compared to a pre-trained codebook, and a corresponding high-quality visual pattern blocks is obtained. The high-quality visual pattern block is then blended with the unrestored image to form a restored image.

Abstract: A method of statistical modeling is provided which includes constructing a statistical model and incorporating Gaussian priors during feature selection and during parameter optimization for the construction of the statistical model.

Abstract: In an information processing apparatus that processes data using cascade-connected weak classifiers, processing specification information specifying the processing content of each of the weak classifiers is stored. The weak classifiers to be used in processing the data are selected from the weak classifiers by referring to a table in which is specified information for determining the weak classifiers to be used based on a condition for processing the data. The data is then processed by the selected weak classifiers based on the processing specification information that corresponds to those weak classifiers, and an object is extracted from the data using an obtained evaluation value. Through this, a combination of extraction process speed and extraction accuracy can be changed in a flexible manner when extracting a specific object from image data.

Abstract: For an enhanced sequential compression of data vectors in a respective compression pass, a current data vector is mapped to at least one current code vector of at least one codebook in at least one quantization stage. The at least one codebook is reordered taking account of at least one intermediate result from the current compression pass and at least one intermediate result from a preceding compression pass. At least one codebook index that is associated in the at least one reordered codebook to the at least one current code vector is then provided for further use. For a decompression of compressed data vectors represented by such codebook indices, at least one codebook index is mapped to at least one code vector of at least one equally reordered codebook.

Abstract: In an encoding process, a CPU transforms an audio signal from the real-time domain to the frequency domain, and transforms the signal into spectra consisting of MDCT coefficients. The CPU separates the audio signal into several frequency bands, and performs bit shifting in each band such that the MDCT coefficients can be expressed with pre-configured numbers of bits. The CPU re-quantizes the MDCT coefficients at a precision differing for each band, and transmits the values acquired thereby and shift bit numbers as encoded data. Meanwhile, in a decoding process, a CPU receives encoded data and inverse re-quantizes and inverse bit shifts the data, thereby restoring the MDCT coefficients. Furthermore, the CPU transforms the data from frequency domain to the real-time domain by using the inverse MDCT, and restores and outputs the audio signal.

Abstract: The restoration of images by vector quantization utilizing visual patterns is disclosed. One disclosed embodiment comprises restoring detail in a transition region of an unrestored image, by first identifying the transition region and forming blurred visual pattern blocks. These blurred visual pattern blocks are compared to a pre-trained codebook, and a corresponding high-quality visual pattern blocks is obtained. The high-quality visual pattern block is then blended with the unrestored image to form a restored image.

Abstract: A noise cancellation apparatus includes a noise estimation module for receiving a noise-containing input speech, and estimating a noise therefrom to output the estimated noise; a first Wiener filter module for receiving the input speech, and applying a first Wiener filter thereto to output a first estimation of clean speech; a database for storing data of a Gaussian mixture model for modeling clean speech; and an MMSE estimation module for receiving the first estimation of clean speech and the data of the Gaussian mixture model to output a second estimation of clean speech. The apparatus further includes a final clean speech estimation module for receiving the second estimation of clean speech from the MMSE estimation module and the estimated noise from the noise estimation module, and obtaining a final Wiener filter gain therefrom to output a final estimation of clean speech by applying the final Wiener filter gain.

Abstract: Provided are, among other things, systems, methods, software programs and techniques for generating an audio thumbnail for a musical piece, in which locations of different repeating segments within an input musical piece are identified. In addition, a singing segment within the musical piece is detected based on a calculated singing metric that indicates when singing is present. A thumbnail criterion that defines a location of an audio thumbnail by reference to generic musical structure is obtained, and a segment of the musical piece is selected as the audio thumbnail based on the thumbnail criterion, together with the location of at least one of the plural different repeating segments and a location of at least a portion of the singing segment. The audio thumbnail is then played and/or stored for future playing.

Abstract: The invention relates to a speech recognition system and method with cepstral noise subtraction. The speech recognition system and method utilize a first scalar coefficient, a second scalar coefficient, and a determining condition to limit the process for the cepstral feature vector, so as to avoid excessive enhancement or subtraction in the cepstral feature vector, so that the operation of the cepstral feature vector is performed properly to improve the anti-noise ability in speech recognition. Furthermore, the speech recognition system and method can be applied in any environment, and have a low complexity and can be easily integrated into other systems, so as to provide the user with a more reliable and stable speech recognition result.

Abstract: A novel system for speech recognition uses differential cepstra over time frames as acoustic features, together with the traditional static cepstral features, for hidden trajectory modeling, and provides greater accuracy and performance in automatic speech recognition. According to one illustrative embodiment, an automatic speech recognition method includes receiving a speech input, generating an interpretation of the speech, and providing an output based at least in part on the interpretation of the speech input. The interpretation of the speech uses hidden trajectory modeling with observation vectors that are based on cepstra and on differential cepstra derived from the cepstra. A method is developed that can automatically train the hidden trajectory model's parameters that are corresponding to the components of the differential cepstra in the full acoustic feature vectors.

Abstract: A system, method and program storage device implementing a method for modeling a data generating process, wherein the modeling comprises observing a data sequence comprising irregularly sampled data, obtaining an observation sequence based on the observed data sequence, assigning a time index sequence to the data sequence, obtaining a hidden state sequence of the data sequence, and decoding the data sequence based on a combination of the time index sequence and the hidden state sequence to model the data sequence. The method further comprises assigning a probability distribution over time stamp values of the observation sequence, wherein the decoding comprises using a Hidden Markov Model. The method further comprises using an expectation maximization methodology to learn the Hidden Markov Model.

Abstract: A database system and a method for case-based reasoning are disclosed. The database system includes an exemplar object within the database configured to accept and store a plurality of exemplar cases, a target object within the database configured to accept and store a target case, and a comparison object within the database for comparing the target case with the plurality of exemplar cases. The method includes comparing the target case with the plurality of exemplar cases within a database to produce similarity metrics and determining the similarity between the target and exemplar cases based on the similarity metrics.