The phrase "audio class" is correct and usable in written English.
It can be used to refer to a category or type of audio content, such as a class of sounds or audio files.
Example: "The audio class for this project includes various sound effects and background music that enhance the overall experience."
Alternatives: "sound category" or "audio category".
The proposed framework adopts a "Divide and Conquer" approach in which an individual network of binary classifiers (NBC) is allocated to discriminate each audio class.
Each audio class has a counterpart in the visual realm, and the relationship of these is shown in the figure below.
Also, for fusion purposes, participants were required to submit the frame-level scores for each non-overlapping audio class.
For that purpose, the participants provided frame-level scores for each non-overlapping audio class for the training and test datasets.
A large set of audio features can be effectively used in the framework, where the CNBCs make appropriate selections and combinations so as to achieve the highest discrimination among individual audio classes.
Both video and audio classes are core components of the M.S. program in which students work on deadline pieces as well as on longer stories.
A major focus was the identification of features suited to segmenting these audio classes: For crosstalk, cross-channel features were explored, while for monaural overlapped speech, energy, harmonic, and spectral features were examined.
For ASR, the segmentation of nonspeech and local speech was the objective while for speaker diarization, nonspeech, single-speaker speech, and overlapped speech were the audio classes to be segmented.
Regular guest speakers in audio classes include: Robert Smith (NPR), Stacey Vanek Smith (NPR), Alex Blumberg (Gimlet), Tim Howard (Gimlet), Luis Trelles (Radio Ambulante), Zoe Chace (This American Life), Ailsa Chang (NPR) and Joe Richman (Radio Diaries).
Fig. 4 The audio classes in telephone channel.
Five audio classes were defined for the evaluation.
