7826 results about "Speech recognition" patented technology

A method for recognizing an audio sample locates an audio file that most closely matches the audio sample from a database indexing a large set of original recordings. Each indexed audio file is represented in the database index by a set of landmark timepoints and associated fingerprints. Landmarks occur at reproducible locations within the file, while fingerprints represent features of the signal at or near the landmark timepoints. To perform recognition, landmarks and fingerprints are computed for the unknown sample and used to retrieve matching fingerprints from the database. For each file containing matching fingerprints, the landmarks are compared with landmarks of the sample at which the same fingerprints were computed. If a large number of corresponding landmarks are linearly related, i.e., if equivalent fingerprints of the sample and retrieved file have the same time evolution, then the file is identified with the sample. The method can be used for any type of sound or music, and is particularly effective for audio signals subject to linear and nonlinear distortion such as background noise, compression artifacts, or transmission dropouts. The sample can be identified in a time proportional to the logarithm of the number of entries in the database; given sufficient computational power, recognition can be performed in nearly real time as the sound is being sampled.

An ontology-based parser incorporates both a system and method for converting natural-language text into predicate-argument format that can be easily used by a variety of applications, including search engines, summarization applications, categorization applications, and word processors. The ontology-based parser contains functional components for receiving documents in a plurality of formats, tokenizing them into instances of concepts from an ontology, and assembling the resulting concepts into predicates. The ontological parser has two major functional elements, a sentence lexer and a parser. The sentence lexer takes a sentence and converts it into a sequence of ontological entities that are tagged with part-of-speech information. The parser converts the sequence of ontological entities into predicate structures using a two-stage process that analyzes the grammatical structure of the sentence, and then applies rules to it that bind arguments into predicates.

A method and system is described which allows users to identify (pre-recorded) sounds such as music, radio broadcast, commercials, and other audio signals in almost any environment. The audio signal (or sound) must be a recording represented in a database of recordings. The service can quickly identify the signal from just a few seconds of excerption, while tolerating high noise and distortion. Once the signal is identified to the user, the user may perform transactions interactively in real-time or offline using the identification information.

A method and apparatus are provided for updating the vocabulary of a speech translation system for translating a first language into a second language including written and spoken words. The method includes adding a new word in the first language to a first recognition lexicon of the first language and associating a description with the new word, wherein the description contains pronunciation and word class information. The new word and description are then updated in a first machine translation module associated with the first language. The first machine translation module contains a first tagging module, a first translation model and a first language module, and is configured to translate the new word to a corresponding translated word in the second language. Optionally, the invention may be used for bidirectional or multi-directional translation

Tapping gestures for selecting text on a device having a touch-sensitive screen are disclosed. A single tap gesture causes a portion of a character string to be selected. A double tap gesture causes the entire character string to be selected. A tap and hold gesture causes the device to enter a cursor mode wherein the placement of a cursor relative to the characters in the character string can be adjusted. In text selection mode, a finger can be used to move the cursor from a cursor start position to a cursor end position to select text therebetween.

A wireless speaker system configured to receive stereo audio information wirelessly transmitted by an audio source including first and second loudspeakers. The first loudspeaker establishes a bidirectional secondary wireless link with the audio source for receiving and acknowledging receipt of the stereo audio information. The first and second loudspeakers communicate with each other via a primary wireless link, and the first and second loudspeakers are configured to extract first and second audio channels, respectively, from the stereo audio information. A wireless audio system including an audio source and first and second loudspeakers, each having a wireless transceiver. The first and second loudspeakers communicate via a primary wireless link. The audio source communicates audio information to the first loudspeaker via a secondary wireless link which is configured according to a standard wireless protocol. The first loudspeaker is configured to acknowledge successful reception of audio information via the secondary wireless link.

A system for automatically providing foreign language abbreviation translation in an instant messaging system that identifies a foreign language abbreviation translation database based on a user indicated source culture. The foreign abbreviation translation database stores abbreviation translations for foreign language abbreviations frequently used by people from the user indicated source culture. The system locates a candidate term in an instant message and compares the candidate term to the foreign language abbreviations in the foreign language abbreviation translation database. In the event that the candidate term matches one of the foreign language abbreviations in the identified foreign language abbreviation translation database, the corresponding translation is retrieved and displayed. The comparison of the candidate term with the foreign language abbreviations may include automatically obtaining a transliteration of the candidate term. The disclosed system advantageously enables translation of foreign language abbreviations to be performed in real-time.

A gesture recognition system includes: elements for detecting and generating a signal corresponding a number of markers arranged on an object, elements for processing the signal from the detecting elements, members for detecting position of the markers in the signal. The markers are divided into first and second set of markers, the first set of markers constituting a reference position and the system comprises elements for detecting movement of the second set of markers and generating a signal as a valid movement with respect to the reference position.

An audio distribution network system (20) allowing an audio distribution system to be created that is integrated with the home automation system into a home network that permits vocal feedback, status and even control with the audio through network speakers (100).

Methods and apparatus for executing a lighting program to control a plurality of light emitting diodes (LEDs) in response to at least one characteristic of an audio input. In one embodiment, the audio input is digitally processed to determine the at least one characteristic. In other embodiments, control signals for the LEDs are generated in response to a timer and/or input from a user interface, as well as in response to the at least one characteristic of the audio input. In another embodiment, the control signals for the LEDs are generated by a same computer that processes the audio input to transmit signals to speakers to audibly play the audio input. In a further embodiment, a GUI is provided to assist in authoring the lighting program. In another embodiment, the audio signal is processed before being played back. In a further embodiment, the lighting program anticipates changes in the audio input.

A method and apparatus for aligning texts. The method includes acquiring a target text and a reference text and aligning the target text and the reference text at word level based on phoneme similarity. The method can be applied to automatically archiving a multimedia resource and a method of automatically searching a multimedia resource.

An audio encoder applies an adaptive block-encoding process to segments of audio information to generate frames of encoded information that are aligned with a reference signal conveying the alignment of a sequence of video information frames. The audio information is analyzed to determine various characteristics of the audio signal such as the occurrence and location of a transient, and a control signal is generated that causes the adaptive block-encoding process to encode segments of varying length. A complementary decoder applies an adaptive block-decoding process to recover the segments of audio information from the frames of encoded information. In embodiments that apply time-domain aliasing cancellation (TDAC) transforms, window functions and transforms are applied according to one of a plurality of segment patterns that define window functions and transform parameters for each segment in a sequence of segments. The segments in each frame of a sequence of overlapping frames may be recovered without aliasing artifacts independently from the recovery of segments in other frames. Window functions are adapted to provide preferred frequency-domain responses and time-domain gain profiles.

Audio coding processes like quantization can cause spectral components of an encoded audio signal to be set to zero, creating spectral holes in the signal. These spectral holes can degrade the perceived quality of audio signals that are reproduced by audio coding systems. An improved decoder avoids or reduces the degradation by filling the spectral holes with synthesized spectral components. An improved encoder may also be used to realize further improvements in the decoder.

The invention is related to methods and apparatus that can advantageously alter a playback rate of a multimedia presentation, such as a video clip. One embodiment of the invention permits a multimedia presentation to be sped up or slowed down with a controlled change in pitch of the sped up or slowed down audio. In one embodiment, this controlled change in the pitch permits the sped up or slowed down audio to retain a same sounding pitch as at normal playback speeds. In one embodiment, a duration is specified and playback of the video clip is advantageously sped to complete playback within the specified duration. In another embodiment, a finish by a time is specified, and the playback of the video clip is advantageously sped to complete playback by the specified time.

Music videos are automatically produced from source audio and video signals. The music video contains edited portions of the video signal synchronized with the audio signal. An embodiment detects transition points in the audio signal and the video signal. The transition points are used to align in time the video and audio signals. The video signal is edited according to its alignment with the audio signal. The resulting edited video signal is merged with the audio signal to form a music video.

A personalized audio system and method that overcomes many of the broadcast-type disadvantages associated with conventional radio stations. According to one embodiment, the personalized audio system includes the following: (1) a user interface that enables a user of the personalized audio system to specify a profile for a personalized audio channel, (2) a sound recording library comprising a plurality of sound recordings, (3) a playlist generator that (a) selects a plurality of sound recording identifiers from a set of sound recording identifiers, wherein each of the plurality of sound recording identifiers identifies a sound recording that matches the profile and that is stored in the library, and that (b) creates a playlist that lists the plurality of sound recording identifiers in a particular order, and (4) a sound recording reproducing device for reproducing the plurality of identified sound recordings according to the particular order in which the sound recording identifiers are listed in the playlist so that the user can listen to the sound recordings. Advantageously, the personalized audio system does not provide the user with a way to determine the plurality of sound recording identifiers prior to the reproducing means reproducing the plurality of sound recordings, and the personalized audio system does not provide the user with a way to directly control which sound recording identifiers in the set are selected by the playlist generator to be included in the plurality of sound recording identifiers.

Method and apparatus for correction of spelling errors in text composition is provided. Correctly spelled words may be determined for an incorrectly spelled word in accordance with a common error approach. Corrections to the incorrectly word are applied using common typographical and spelling errors. Resulting words which are correctly spelled may be offered as replacements or automatically used to replace the incorrectly word. Corrections may be applied in response to a frequency of the error in text composition to generate correct words that are more likely to be the word intended to be composed. The specific order of application may be configurable to meet a user's preference or a learned behavior for a user.

A preference determination system allows a music provider, like a band or disc jockey, to determine the musical preferences of the members at a gathering. As many members of a gathering use electronic devices, like cellular telephones, that include music and video players, these devices include a corresponding play list that includes information about the music or video. When at a gathering the music provider, for example, interrogates the devices of the members of the group and uploads their respective play lists. The music provider then compiles information about the music into a data compilation. The information may include artist, song title, release date, genre, etc. The music provider then sorts the data compilation to select information that is popular to a significant number of members in the group. The music provider then selects and plays music to the group consistent with the selected information. For example, if 50 people are at a gathering, and 30 have digital music by the Tom Waits on their devices, the music provider may decide to play “Innocent When You Dream” for the group.

A method for coding or decoding an audio signal combines the advantages of TNS processing and noise substitution. A time-discrete audio signal is initially transformed to the frequency domain in order to obtain spectral values of the temporal audio signal. Subsequently, a prediction of the spectral values in relation to frequency is carried out in order to obtain spectral residual values. Within the spectral residual values, areas are detected encompassing spectral residual values with noise properties. The spectral residual values in the noise areas are noise-substituted, whereupon information concerning the noise areas and noise substitution is incorporated into side information pertaining to a coded audio signal. Thus, considerable bit savings in case of transient signals can be achieved.

A system for, and method of, representing and resolving ambiguity in natural language text and a spoken dialogue system incorporating the system for representing and resolving ambiguity or the method. In one embodiment, the system for representing and resolving ambiguity includes: (1) a context tracker that places the natural language text in context to yield candidate attribute-value (AV) pairs and (2) a candidate scorer, associated with the context tracker, that adjusts a confidence associated with each candidate AV pair based on system intent.

An audio fingerprint is extracted from an audio sample, where the fingerprint contains information that is characteristic of the content in the sample. The fingerprint may be generated by computing an energy spectrum for the audio sample, resampling the energy spectrum logarithmically in the time dimension, transforming the resampled energy spectrum to produce a series of feature vectors, and computing the fingerprint using differential coding of the feature vectors. The generated fingerprint can be compared to a set of reference fingerprints in a database to identify the original audio content.

A text message generated at a sending device is converted into audio form by a message-conversion system for delivery to a target recipient. This conversion is effected in a manner enabling emotions, encoded by indicators embedded in the text message, to be expressed through multiple types of presentation feature in the audio form of the message. The mapping of emotions to feature values is pre-established for each feature type whilst the sender selection of one or more feature types to be used to express encoded emotions is specified by type indications inserted into the message at its time of generation.

A system-level text correction service (330) is provided. The service (330) includes monitoring (410) the input of text (340) on a computer system, identifying an incorrect input word in a first application. Correction proposal words are retrieved from a system-level dictionary (320), wherein the system-level dictionary (320) stores a reference word with an identifier of at least one application type in which the reference word is used. The correction proposal words are ranked according to the similarity of the proposal word to the input word and by comparing the first application to the application types of the reference word.

The invention discloses a control method and apparatus of multiple voice assistants, and a computer readable storage medium, aiming at solving the technical problem that when current electronic equipment switches voice assistants, the current electronic equipment needs to enable the voice assistants manually and the switching mode is not flexible. The control method of multiple voice assistants isapplied to electronic equipment integrated with multiple voice assistants, and includes the steps: when detecting a trigger event for wakening the voice assistants, according to the trigger event, determining the target voice assistant from the multiple voice assistants, wherein the wakening functions of the multiple voice assistants are in the enabled state; and wakening the target voice assistant.

The present invention extends to methods, systems, and computer program products for recognizing input gestures. A neural network is trained using example inputs and backpropagation to recognize specified input patterns. Input gesture data is representative of movements in contact on a multi-touch input display surface relative to one or more axes over time. Example inputs used for training the neural network to recognize a specified input pattern can be created from sampling input gesture data for example input gestures known to represent the specified input pattern. Trained neural networks can subsequently be used to recognize input gestures that are similar to known input gestures as the specified input pattern corresponding to the known input gestures.

Method and apparatus for identifying broadcast digital audio signals include structure and/or function whereby the digital audio signal is provided to processing structure which is configured to (i) identify a program-identifying code in the received digital audio signal, (ii) identify a program-identifying code in a decompressed received digital audio signal, (iii) identify a feature signature in the received digital audio signal, and (iv) identify a feature signature in the decompressed received digital audio signal. Preferably, such processing structure is disposed in a dwelling or a monitoring site in an audience measurement system, such as the Nielsen TV ratings system.

Machine translation decoding is accomplished by receiving as input a text segment in a source language to be translated into a target language, generating an initial translation as a current target language translation, applying one or more modification operators to the current target language translation to generate one or more modified target language translations, determining whether one or more of the modified target language translations represents an improved translation in comparison with the current target language translation, setting a modified target language translation as the current target language translation, and repeating these steps until occurrence of a termination condition. Automatically generating a tree (e.g., either a syntactic tree or a discourse tree) can be accomplished by receiving as input a tree corresponding to a source language text segment, and applying one or more decision rules to the received input to generate a tree corresponding to a target language text segment.

A mobile phone with music reproduction function has a reproduction unit that reproduces music data and a ring tone which are recorded in a music data recording medium, and a communication unit 108 that detects an incoming call from outside. The mobile phone 100 has a control unit that instructs the reproduction unit to perform a fade-out process of reproducing the music data and to perform a fade-in process of outputting the ring tone when the communication unit detects an incoming call while the reproduction unit is reproducing music data.

<heading lvl="0">Abstract of Disclosure</heading> When the user enters a word in a document, the word is parsed. If the word is misspelled, a static update list is checked to see if the misspelled word has an automatic correction. If the word is not in the static update list and the user corrects the misspelling, the misspelled word and the correction are both captured in a list. If the user corrects the misspelling a sufficient number of times, the static update list can itself be dynamically updated to recognize the correction regularly entered by the user.

The method and apparatus identifies selected broadcast segments, such as commercial advertisements, of a television signal in real-time for the purpose of muting the video and audio portions of the television signal during each unwanted segment. A signature pattern associated with each segment of the television signal is detected and compared to stored signature patterns representative of selected segments such as commercial advertisement segments. If the signature pattern matches one of the stored signature patterns, the segment is thereby immediately identified as being one of the selected segments and is processed in real-time to mute the audio and video portions of the television signal during the segment. If the signature pattern of the segment does not match any of the stored signature patterns, the segment is analyzed to determine whether the segment is nevertheless a selected segment and, if so, its signature pattern is stored along with the stored signature patterns. The analysis to determine whether the segment is nevertheless a selected segment is performed by detecting the length of the segment upon its completion and then determining whether the length of the segment matches one of a pre-determined set of permissible selected segment lengths such as standard commercial advertisement segments of 15 seconds, 30 seconds, or 60 seconds. If so, the segment is identified as being a selected and its signature pattern is stored along with the other stored signature patterns such that, the next time the same segment is encountered, its signature will then match the stored signature and therefore the segment can be immediately identified and muted in real-time.