549 results about "Audio recognition" patented technology

Method and apparatus that use voice/audio recognition and analysis technologies to deliver assigned context sensitive information and data of interest (keywords, phrases, mood, etc.). Context sensitive information and data of interest can be extracted from any voice/audio transmissions and voice/audio recordings (or any transmission or recording that includes voice/audio) for advertising purposes. This invention includes the said assigned context sensitive information and data of interest extraction method using voice/audio recognition and analysis technologies. Most importantly, this invention opens up new doors to advertising using extracted context sensitive information and data of interest from voice/audio transmissions and recordings (or any transmission that includes voice/audio).

Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

Audio signal processing enhances audio watermark embedding and detecting processes. Audio signal processes include audio classification and adapting watermark embedding and detecting based on classification. Advances in audio watermark design include adaptive watermark signal structure data protocols, perceptual models, and insertion methods. Perceptual and robustness evaluation is integrated into audio watermark embedding to optimize audio quality relative the original signal, and to optimize robustness or data capacity. These methods are applied to audio segments in audio embedder and detector configurations to support real time operation. Feature extraction and matching are also used to adapt audio watermark embedding and detecting.

An audio fingerprint is generated by transforming an audio sample of a recording to a time-frequency domain and storing each time-frequency pair in a matrix array, detecting a plurality of local maxima for a predetermined number of time slices, selecting a predetermined number of largest-magnitude maxima from the plurality of local maxima detected by said detecting, and generating one or more hash values corresponding to the predetermined number of largest-magnitude maxima.

Controlling a multimedia software application using high-level metadata features and symbolic object labels derived from an audio source, wherein a first-pass of low-level signal analysis is performed, followed by a stage of statistical and perceptual processing, followed by a symbolic machine-learning or data-mining processing component is disclosed. This multi-stage analysis system delivers high-level metadata features, sound object identifiers, stream labels or other symbolic metadata to the application scripts or programs, which use the data to configure processing chains, or map it to other media. Embodiments of the invention can be incorporated into multimedia content players, musical instruments, recording studio equipment, installed and live sound equipment, broadcast equipment, metadata-generation applications, software-as-a-service applications, search engines, and mobile devices.

The present invention relates to the continuous monitoring of an audio signal and identification of audio items within an audio signal. The technology disclosed utilizes predictive caching of fingerprints to improve efficiency. Fingerprints are cached for tracking an audio signal with known alignment and for watching an audio signal without known alignment, based on already identified fingerprints extracted from the audio signal. Software running on a smart phone or other battery-powered device cooperates with software running on an audio identification server.

A method obtains media on a device, provides identification of an object in the media via image/video recognition and audio recognition, and displays on the device identification information based on the identified media object.

A novel video surveillance system is made up of video and audio compression engine, a storage device and, a video and audio recognition engine. The video recognition engine detects such events as face recognition, motion detection etc, whereas audio recognition engine detects voice and other sound signatures indicating a potential alarm situation, e.g., panic voices such as screaming and yelling, or sounds such as gun shots, explosions. Combined recognition of audio and video signals provides for higher true alarm generation and lower false alarms level of the surveillance system. Additionally, the audio recognition engine provides information for directing video cameras in the direction of interest allowing better capture of an interesting scene.

System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. The semantic information may be associated with audio signature data

Extracted audio features that are most similar to one or more templates from the comparison are identified according to the tagged information. The tags are used to determine the semantic audio data that includes genre, instrumentation, style, acoustical dynamics, and emotive descriptor for the audio signal.

Techniques are disclosed for automatically de-identifying spoken audio signals. In particular, techniques are disclosed for automatically removing personally identifying information from spoken audio signals and replacing such information with non-personally identifying information. De-identification of a spoken audio signal may be performed by automatically generating a report based on the spoken audio signal. The report may include concept content (e.g., text) corresponding to one or more concepts represented by the spoken audio signal. The report may also include timestamps indicating temporal positions of speech in the spoken audio signal that corresponds to the concept content. Concept content that represents personally identifying information is identified. Audio corresponding to the personally identifying concept content is removed from the spoken audio signal. The removed audio may be replaced with non-personally identifying audio.

The invention discloses a method for identifying local discharge signals of a switchboard based on a support vector machine model. The method comprises a model training process and an audio identifying process, and particularly comprises the following steps of: preprocessing audio signals; extracting effective audios according to short-time energy and a zero-crossing rate; segmenting the effective audios and extracting characteristic parameters such as Mel cepstrum coefficients, first order difference Mel cepstrum coefficients, high zero-crossing rate and the like of each segment of the audios; training a sample set by using a support vector machine tool, and establishing a corresponding support vector machine model; after preprocessing audio signals to be identified and extracting and segmenting the effective audios, classifying and identifying segment-characteristic-based samples to be tested according to the support vector machine model; and post-processing classification results, and judging whether partial discharge signals exist. By using the method, the existence of the partial discharge signals of the switchboard is accurately identified, the happening of major accidents involving electricity is prevented and avoided, economic losses caused by insulation accidents are reduced, and the power distribution reliability is improved.

System, apparatus and method for determining semantic information from audio, where incoming audio is sampled and processed to extract audio features, including temporal, spectral, harmonic and rhythmic features. The extracted audio features are compared to stored audio templates that include ranges and/or values for certain features and are tagged for specific ranges and/or values. Extracted audio features that are most similar to one or more templates from the comparison are identified according to the tagged information. The tags are used to determine the semantic audio data that includes genre, instrumentation, style, acoustical dynamics, and emotive descriptor for the audio signal.

The user interface for a mobile communication device may be provided based on the current context of a voice session, as recognized by an automated audio recognition engine. In one implementation, the mobile device may transcribe, by an audio recognition engine in the mobile device, audio from a voice session conducted through the mobile device; detect, by the mobile device and based at least on the transcribed audio, changes in context during the voice session that relate to a change in functionality of the user interface of the mobile device; and update, by the mobile device, the user interface in response to the detected change in context.

A Ring Tone is downloaded to a mobile terminal that combines both a musical portion selected by a subscriber/purchaser as well as an audio identification portion that is associated with the identity of a caller and is customized by the subscriber/purchaser. For example, the audio identification portion can be a recording of the caller's name or a “pet” name or nickname associated with that caller, or any sound that the subscriber/purchaser chooses to identify the caller. Thus, when an incoming call from that caller is received by the subscriber's/purchaser's mobile terminal and is recognized from its caller ID as being one that is stored in the mobile terminal's address book with an associated Ring Tone, the Ring Tone that is played includes both a musical portion and an audio portion that audibly identifies the caller. The subscriber/purchaser can thus immediately and unambiguously identify the caller.

A system and method of identifying an audio track uses music identification software that produces a fingerprint or audio profile for an audio segment recorded with a portable communication device. The audio profile is transmitted from the portable communication device to a remote service provider over a communication network. The remote server receives the transmitted audio track profile and compares the profile to a stored database of audio tracks. If a matching audio track is identified by the remote server, metadata relating to the identified audio track is transmitted from the remote server to the portable communication device. The received audio track metadata is then displayed on the portable communication device.

The invention provides a method for obtaining information. The method comprises the following steps that: sound is detected and collected, and then, events are triggered; the sound, played in real time in the environment, of the current channel is collected, and audio data is obtained; the audio data or audio feature information or audio fingerprints are sent to a server, so that the server obtains the audio fingerprints, and a matched channel mark corresponding to the channel audio fingerprints matched with the audio fingerprints is determined according to a real-time buffered channel audio fingerprint database; and preset information which corresponds to the matched channel mark, is obtained from the preset information database and is sent by the server is received. When the method for obtaining information provided by the invention is utilized, the audio identification can be carried out through the server only through triggering the collected sound on a user terminal, further, relevant information of programs playing in the current channel can be obtained, and the information obtaining efficiency is greatly improved. The invention also provides a device for obtaining the information, a method for pushing the information, a device for pushing the information and an information interaction system.

The invention provides an audio/video processing device and an audio/video processing method. The audio/video processing device comprises a receiving unit, a decoding unit, a user interface unit, an information extracting unit and an information storage unit, wherein the receiving unit receives signals and outputs transmission streams; the decoding unit decodes the output transmission streams; the user interface unit receives a determined content output by users; the information extracting unit extracts a prescribed content; and the information storage unit stores the prescribed content, wherein the determined content includes a determined video content or determined audio content, and the alternative one is determined by an audio/video contrasting relation table. The information extracting unit comprises an audio identification unit, a video identification unit and an information matching unit, wherein the audio identification unit identifies the determined audio content from audio steams from the decoding unit; the video identification unit identifies the determined video content from video steams from the decoding unit; the information matching unit determines if an identification result of the audio identification unit is matched with an identification result of the video identification unit, and when the identification result of the audio identification unit is matched with the identification result of the video identification unit, the information matching unit records the prescribed content which corresponds to the determined video content or the determined audio consent in the information storage unit.

The invention relates to an intelligent interaction system and method. The system includes an audio receiving module, a real-time processing module and an execution module, wherein the audio receiving module is used for receiving audio information inputted by a user, the real-time processing module is used for performing parallel online real-time processing on the audio information, and the execution module is used for executing corresponding operation according to identification results transmitted by the real-time processing module. The parallel online real-time processing includes the following steps that: classification processing and identification processing corresponding to different types are performed on the audio information; if credible classification types are obtained before the ending of audio input, identification processing on classification types except the credible classification types is terminated; identification results corresponding to the credible classification types can be obtained and are transmitted to the execution module. With the intelligent interaction system and method of the invention adopted, the user can use audio identification and voice interaction functions easily and quickly, and user experience can be enhanced.

The present invention provides a video feature extraction method, a video feature extraction device and a computer device. The video feature extraction method includes the following steps that: a target video is divided according to a predetermined unit time length; at least two frames of images included in video segments are obtained; the at least two frames of images are identified, feature information contained in the images is obtained, and the image feature information of the video segments is obtained according to the feature information included in the images; the text feature information of the video segments is obtained according to the caption recognition result of each frame of image and the real-time speech recognition result of the video segments; semantic analysis is performed, so that the feature information of the video segments is obtained; and a mapping relationship between the feature information of the video segments and the target video is established. With the video feature extraction method, the video feature extraction device and the computer device of the invention adopted, the feature information of the video can be automatically extracted through image video and audio recognition technology, and the extraction of the feature information is refined to the dimension of the video segments of unit time length in the video, and therefore, the obtained feature information is more comprehensive.

The invention discloses an audio recognition method and an audio recognition device, and relates to the field of audio technologies. The method comprises the steps of intercepting an audio stream with a first time length from the source data of a video file; and obtaining corresponding audio information through retrieving according to the audio stream with the first time length, and showing to a user, wherein the step of obtaining the corresponding audio information through retrieving according to the audio stream with the first time length comprises dividing the audio stream into at least two sub-audio streams according to a preset rule, and sequentially retrieving the sub-audio streams obtained through dividing to obtain the audio information. According to the audio recognition method, the audio stream can be directly extracted from the current played video source data for retrieval without additional recording operation and influence of a noisy environment, the operation is simple, the accuracy rate is high, the retrieval process does not influence the user to normally watch the video, and the retrieval efficiency and the success rate of retrieval can be improved.

The invention belongs to the technical field of audio processing, and relates to an extensible audio recognition system based on man-machine interaction and a method thereof. The extensible audio recognition system comprises an audio acquisition device, a voice recognition module, a loading sample unit, a finite-state machine, a classification storage characteristic sample database and an instruction execution module. The audio recognition method is based on high recognition rate of isolate word speed recognition to a speaker dependent, and enables the system to store voice segments which can not be recognized into the sample database in an online learning mode after a process of man-machine interaction through the assistance of a user on the premise of fully training the user, and in addition, the cost to recognition is reduced through divided module storage and loading. The core algorithm of the invention is based on voice signals, is not limited to languages of speakers, and can support the recognition of mixed languages (for example, Chinese and English and the like). The method has lower false recognition rate and no recognition rate, and improves the reliability and adaptability of the system through dialogue interaction and online increment training.