Sentence examples for audio context from inspiring English sources

In the first stage, audio context of the tested signal is recognized.

In the first stage, the recording is tested for audio context classification.

We achieve this by implementing a first stage for audio context recognition and event set selection.

It is noted that the third best system used SDC coefficients, which take into account a long audio context.

The symbolic information about the sound events can be used in other research areas, e.g., audio context recognition [8, 9], automatic tagging [10], and audio segmentation [11].

As discussed in Section 2, an audio context can be recognized robustly among a small and restricted set of context classes.

Sound event detection for a wider set of real-world audio contexts was studied in [27].

The DARES-G1 database [39] published in 2009 offers a more diverse set of audio recordings from many audio contexts.

A system based on Mel-frequency cepstral coefficients (MFCC) features and an HMM classifier achieved on average a 30% detection accuracy over ten real-world audio contexts.

The recordings for the database were collected from ten audio contexts: basketball game, beach, inside a bus, inside a car, hallways, inside an office facility, restaurant, grocery shop, street, and stadium with track and field events.

In addition to this, usually a low number of sound categories are involved in the studies, specifically chosen to minimize overlapping between different categories, and evaluations are carried out with one or very small set of audio contexts (kitchen [20], bathroom [21], meeting room [22], office and canteen [23]).