Abstract: An interactive system, a display apparatus, and a controlling method are provided. The display apparatus includes an input which receives an uttered voice of a user; a communicator which transmits a voice signal of the uttered voice to a voice recognition apparatus; a voice recognizer which performs a voice recognition process with the uttered voice; and a controller which determines first or second voice information which has a reliability value greater than or equal to a preset threshold value among a reliability value of the first voice information, and a reliability value of the second voice information to be an execution command of the uttered voice. Therefore, if the display apparatus and an external apparatus simultaneously recognize the uttered voice of the user, the display apparatus selects a voice recognition result proximate to an intent of the user from two voice recognition results.

Abstract: An audio system processes a speech signal to maintain a target value of the speech intelligibility index (SII) while minimizing the overall speech level so that speech intelligibility is preserved across different environmental sound levels while possible distortions and overall loudness are mitigated. In one embodiment, a hearing aid processes a speech signal received from another device to maintain a target value of the SII while minimizing the overall speech level before mixing the speech signal with a microphone signal.

Abstract: Techniques for receiving a voice command from a user and, in response, providing audible content to the user via a first device and providing visual content for the user via a second device. In some instances, the first device includes a microphone for generating audio signals that include user speech, as well as a speaker for outputting audible content in response to identified voice commands from the speech. However, the first device might not include a display for displaying graphical content. As such, the first device may be configured to identify devices that include displays and that are proximate to the first device. The first device may then instruct one or more of these other devices to output visual content associated with a user's voice command.

Abstract: Methods and systems for providing auditory messages for medical devices are provided. One method includes receiving semantic rating scale data corresponding to a plurality of sounds and medical message descriptions and performing semantic mapping using the received semantic rating scale data. The method also includes determining profiles for audible medical messages based on the semantic mapping and generating audible medical messages based on the determined profiles.

Abstract: A method of communicating between a sender and a recipient via a personalized message is disclosed comprising: (a) identifying text, via the user interface of a communication device, of a desired lyric phrase from within a pre-existing audio recording; (b) extracting audio substantially associated with the desired lyric phrase from the pre-existing recording into a desired audio clip; (c) inputting personalized text via the user interface; (d) creating the personalized message with the sender identification, the personalized text and access to the desired audio clip; (e) sending an electronic message to the electronic address of the recipient, wherein the electronic message may be an SMS/EMS/MMS message, instant message or email message including a link to the personalized message or an EMS/MMS or email message including the personalized message. An associated method of earning money from the communication along with associated systems are also disclosed.

Abstract: The present invention relates to a searching device, searching method, and program whereby searching for a word string corresponding to input voice can be performed in a robust manner. A voice recognition unit 11 subjects an input voice to voice recognition. A matching unit 16 performs matching, for each of multiple word strings for search results which are word strings that are to be search results for word strings corresponding to the input voice, of a pronunciation symbol string for search results, which is an array of pronunciation symbols expressing pronunciation of the word string search result, and a recognition result pronunciation symbol string which is an array of pronunciation symbols expressing pronunciation of the voice recognition results of the input voice.

Abstract: A method of communicating between a sender and a recipient via a personalized message is disclosed comprising: (a) identifying text, via the user interface of a communication device, of a desired lyric phrase from within a pre-existing audio recording; (b) extracting audio substantially associated with the desired lyric phrase from the pre-existing recording into a desired audio clip; (c) inputting personalized text via the user interface; (d) creating the personalized message with the sender identification, the personalized text and access to the desired audio clip; (e) sending an electronic message to the electronic address of the recipient, wherein the electronic message may be an SMS/EMS/MMS message, instant message or email message including a link to the personalized message or an EMS/MMS or email message including the personalized message. An associated method of earning money from the communication along with associated systems are also disclosed.

Abstract: The present invention discloses a method and apparatus for speech synthesis based on a large corpus. The method for speech synthesis based on a large corpus comprises: utilizing a prosodic structure prediction model to carry out prosodic structure prediction processing on input text to provide at least one alternative prosodic boundary partitioning solution; determining a prosodic boundary partitioning solution according to structure probability information about a prosodic unit in a speech corpus in the at least one alternative prosodic boundary partitioning solution; and carrying out speech synthesis according to the determined prosodic boundary partitioning solution. The method and apparatus for speech synthesis based on a large corpus provided by the embodiments of the present invention improve the naturalness and flexibility of speech synthesis.

Abstract: The technology of the present application provides a speech recognition system with at least two different speech recognition engines or a single engine speech recognition engine with at least two different modes of operation. The first speech recognition being used to match audio to text, which text may be words or phrases. The matched audio and text is used by a training module to train a user profile for a natural language speech recognition engine, which is at least one of the two different speech recognition engines or modes. An evaluation module evaluates when the user profile is sufficiently trained to convert the speech recognition engine from the first speech recognition engine or mode to the natural language speech recognition or mode.

Abstract: The present invention, pertaining to the field of speech recognition, discloses a reminder setting method and apparatus. The method includes: acquiring speech signals; acquiring time information in speech signals by using keyword recognition, and determining reminder time for reminder setting according to the time information; acquiring text sequence corresponding to the speech signals by using continuous speech recognition, and determining reminder content for reminder setting according to the time information and the text sequence; and setting a reminder according to the reminder time and the reminder content.

Abstract: The present invention provides a real-time multimedia event reporting system and method that enable reporters to generate accurate reports or contents simultaneously in multiple languages accessible by users from anywhere in any form in real-time as the live event proceeds. In addition, the present invention enables the generation of a multi-language report in which words uttered during the event are represented in the languages that they were spoken. The disclosed system also enhances the real-time performance of the reporting process by enabling dynamic adjustment to the speech transcription operating parameters and by providing real-time editing of transcribed text using configurable event-specific text representations.

Abstract: A particular method includes determining, based on an inter-line spectral pair (LSP) spacing corresponding to an audio signal, that the audio signal includes a component corresponding to an artifact-generating condition. The method also includes, in response to determining that the audio signal includes the component, adjusting a gain parameter corresponding to the audio signal. For example, the gain parameter may be adjusted via gain attenuation and/or gain smoothing.

Abstract: Voice-based input is used to operate a media device and/or to search for media content. Voice input is received by a media device via one or more audio input devices and is translated into a textual representation of the voice input. The textual representation of the voice input is used to search one or more cache mappings between input commands and one or more associated device actions and/or media content queries. One or more natural language processing techniques may be applied to the translated text and the resulting text may be transmitted as a query to a media search service. A media search service returns results comprising one or more content item listings and the results may be presented on a display to a user.

Abstract: A speech recognition platform configured to receive an audio signal that includes speech from a user and perform automatic speech recognition (ASR) on the audio signal to identify ASR results. The platform may identify: (i) a domain of a voice command within the speech based on the ASR results and based on context information associated with the speech or the user, and (ii) an intent of the voice command. In response to identifying the intent, the platform may perform multiple actions corresponding to this intent. The platform may select a target action to perform, and may engage in a back-and-forth dialog to obtain information for completing the target action. The action may include streaming audio to the device, setting a reminder for the user, purchasing an item on behalf of the user, making a reservation for the user or launching an application for the user.

Abstract: A particular method includes determining, based on spectral information corresponding to an audio signal that includes a low-band portion and a high-band portion, that the audio signal includes a component corresponding to an artifact-generating condition. The method also includes filtering the high-band portion of the audio signal and generating an encoded signal. Generating the encoded signal includes determining gain information based on a ratio of a first energy corresponding to filtered high-band output to a second energy corresponding to the low-band portion to reduce an audible effect of the artifact-generating condition.

Abstract: A particular method includes determining, at a device, a voicing classification of an input signal. The input signal corresponds to an audio signal. The method also includes controlling an amount of an envelope of a representation of the input signal based on the voicing classification. The method further includes modulating a white noise signal based on the controlled amount of the envelope. The method also includes generating a high band excitation signal based on the modulated white noise signal.

Abstract: A security device for hindering data theft and data leaks via audio channel of a computer system is based on passing the audio signals through a coding vocoder that receives input audio signal from a computer and compressing the signal to a low bit-rate digital data indicative of human speech; and a decoding vocoder that decompress the digital data back to a secure audio signal. The data transfer of the protected audio channel is intentionally limited not to exceed the bit-rate needed to carry vocoder-compressed human speech which is well below the capabilities of unprotected audio channel. Both analog and digital audio ports may be protected. Hardware bit-rate limiter protect the system from software hacking.

Abstract: An electronic device for browsing a document is disclosed. The document being browsed includes a plurality of command-associated text strings. First, a text string selector of the electronic device selects a plurality of candidate text strings from the command-associated text strings. Afterward, an acoustic string provider of the electronic device prepares a candidate acoustic string for each of the candidate text strings. Thereafter, a microphone of the electronic device receives a voice command. Next, a speech recognizer of the electronic device searches the candidate acoustic strings for a target acoustic string that matches the voice command, wherein the target acoustic string corresponds to a target text string of the candidate text strings. Finally, a document browser of the electronic device executes a command associated with the target text string.

Abstract: Systems and methods are provided for training language models using in-domain-like data collected automatically from one or more data sources. The data sources (such as text data or user-interactional data) are mined for specific types of data, including data related to style, content, and probability of relevance, which are then used for language model training. In one embodiment, a language model is trained from features extracted from a knowledge graph modified into a probabilistic graph, where entity popularities are represented and the popularity information is obtained from data sources related to the knowledge. Embodiments of language models trained from this data are particularly suitable for domain-specific conversational understanding tasks where natural language is used, such as user interaction with a game console or a personal assistant application on personal device.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a dialog system using user feedback. According to one implementation, a method includes receiving, by a dialog engine, a first input that specifies a question; providing, by the dialog engine, an answer to the question; receiving, by the dialog engine, a second input; and determining, by the dialog engine, that the second input is classified as feedback to the answer, then determining a feedback score associated with the second input.