Abstract: Techniques are disclosed for securely classifying or decoding data. By way of example, a method of determining a most likely sequence for a given data set comprises a computer system associated with a first party performing the following steps. An encrypted model is obtained from a second party. The encrypted model is utilized to determine cost values associated with a particular sequence of observed outputs associated with the given data set. The cost values are sent to the second party. At least one index of a minimum cost value determined by the second party from the cost values sent thereto is obtained from the second party. A minimum cost sequence resulting from the at least one index is determined as the most likely sequence.

Abstract: Methods and systems for speech recognition processing are described. In an example, a computing device may be configured to receive information indicative of a frequency of submission of a search query to a search engine for a search query composed of a sequence of words. Based on the frequency of submission of the search query exceeding a threshold, the computing device may be configured to determine groupings of one or more words of the search query based on an order in which the one or more words occur in the sequence of words of the search query. Further, the computing device may be configured to provide information indicating the groupings to a speech recognition system.

Abstract: Methods and systems for speech recognition processing are described. In an example, a computing device may be configured to receive information indicative of a frequency of submission of a search query to a search engine for a search query composed of a sequence of words. Based on the frequency of submission of the search query exceeding a threshold, the computing device may be configured to determine groupings of one or more words of the search query based on an order in which the one or more words occur in the sequence of words of the search query. Further, the computing device may be configured to provide information indicating the groupings to a speech recognition system.

Abstract: A computer-implemented technique for transcribing audio data includes generating, along a vertical axis on a display of a client device, an image representing audio content. The technique further includes receiving, from a user of the client device, a selection of a portion of the image; and generating, via an audio module of the client device, an audio output corresponding to the selected portion of the image. The technique further includes receiving, from the user, a selection indicating a position along the vertical axis on the display to enter a text portion representing the audio output, wherein the position is aligned to the selected portion of the image. The technique further includes receiving, from the user, the text portion representing the audio output; and displaying, on the display, the text portion at the position, wherein the text portion extends along a horizontal axis on the display.

Abstract: Methods and systems for speech recognition processing are described. In an example, a computing device may be configured to receive information indicative of a frequency of submission of a search query to a search engine for a search query composed of a sequence of words. Based on the frequency of submission of the search query exceeding a threshold, the computing device may be configured to determine groupings of one or more words of the search query based on an order in which the one or more words occur in the sequence of words of the search query. Further, the computing device may be configured to provide information indicating the groupings to a speech recognition system.

Abstract: Techniques are disclosed for securely classifying or decoding data. By way of example, a method of determining a most likely sequence for a given data set comprises a computer system associated with a first party performing the following steps. An encrypted model is obtained from a second party. The encrypted model is utilized to determine cost values associated with a particular sequence of observed outputs associated with the given data set. The cost values are sent to the second party. At least one index of a minimum cost value determined by the second party from the cost values sent thereto is obtained from the second party. A minimum cost sequence resulting from the at least one index is determined as the most likely sequence.

Abstract: Methods and apparatus are provided for processing an information signal containing content presented in accordance with at least one modality. In one aspect of the present invention, a method of processing an information signal containing content presented in accordance with at least one modality, comprises the steps of: (i) obtaining the information signal; (ii) performing content detection on the information signal to detect whether the information signal includes particular content presented in accordance with the at least one modality; and (iii) generating a control signal, when the particular content is detected, for use in controlling a rendering property of the particular content and/or implementation of a specific action relating to the particular content.

Abstract: Apparatus for presenting images representative of one or more words in an utterance with corresponding decoded speech includes, in one aspect, a visual detector for capturing images of body movements (e.g., lip and/or mouth movements) corresponding to the one or more words in the utterance coupled to a visual feature extractor. The visual feature extractor receives time information from an automatic speech recognition (ASR) system and operatively processes the captured images from the visual detector to generate one or more image segments based on the time information relating to one or more decoded words in the utterance, each image segment corresponding to a decoded word in the utterance. An image player coupled to the visual feature extractor presents an image segment with a corresponding decoded word.

Abstract: Methods and apparatus for encoding an arbitrary digital message, e.g., a watermark, into a speech signal are provided. In one aspect of the invention, a method of embedding digital information in a speech signal comprises the steps of: (i) generating a spread spectrum signal, wherein the spread spectrum signal is representative of the digital information and further wherein the spread spectrum signal is within a frequency bandwidth corresponding to speech; and (ii) embedding the spread spectrum signal in the speech signal. By making use of spread spectrum technology and speech analysis techniques in the signal generation and embedding operations, respectively, significantly higher bit rates can be embedded into the speech signal without effecting the perceived quality of the recording. The invention also provides methods and apparatus for recovering the digital information embedded in the speech signal.

Abstract: A multi-channel telephone data collection, collaboration and conferencing system for use with a plurality of telephone channels, the telephone channels being interconnected to facilitate a conference call between a plurality of telephone conferencing devices, the system comprising: a call processor having at least two telephone conferencing device input/output ports connected to the processor and to the plurality of telephone conferencing devices, the call processor generates an audio signal corresponding to each of the plurality of telephone conferencing devices connected to the telephone input/output ports; an audio saving module, connected to the call processor, that converts the audio signal corresponding to each of the plurality of telephone conferencing devices to a digital signal; a memory device that stores the digital signals corresponding to each conference device; an audio switch, connected to the call processor and the memory device, that has a plurality of audio inputs corresponding to each of th

Abstract: A method for collecting data associated with the voice of a voice system user includes conducting a plurality of conversations with a plurality of voice system users. For each conversation, a speech waveform is captured and digitized, and at least one acoustic feature is extracted. The features are correlated with at least one attribute such as gender, age, accent, native language, dialect, socioeconomic classification, educational level and emotional state. Attribute data and at least one identifying indicia are stored for each user in a data warehouse, in a form to facilitate subsequent data mining thereon. The resulting collection of stored data is then mined to provide information for modifying underlying business logic of the voice system. An apparatus suitable for carrying out the method includes a dialog management unit, an audio capture module, an acoustic from end, a processing module and a data warehouse.

Abstract: Apparatus for presenting images representative of one or more words in an utterance with corresponding decoded speech includes, in one aspect, a visual detector for capturing images of body movements (e.g., lip and/or mouth movements) corresponding to the one or more words in the utterance coupled to a visual feature extractor. The visual feature extractor receives time information from an automatic speech recognition (ASR) system and operatively processes the captured images from the visual detector to generate one or more image segments based on the time information relating to one or more decoded words in the utterance, each image segment corresponding to a decoded word in the utterance. An image player coupled to the visual feature extractor presents an image segment with a corresponding decoded word.

Abstract: A method of identifying homophones of a word uttered by a user from at least a portion of existing words of a vocabulary of a speech recognition engine comprises the steps of: a user uttering the word; decoding the uttered word; computing respective measures between the decoded word and at least a portion of the other existing vocabulary words, the respective measures indicative of acoustic similarity between the word and the at least a portion of other existing words; if at least one measure is within a threshold range, indicating, to the user, results associated with the at least one measure, the results preferably including the decoded word and the other existing vocabulary word associated with the at least one measure; and the user preferably making a selection depending on the word the user intended to utter.