Method of audio error detection

Errors in audio outputs during gameplay are detected by providing an audio output distribution of confirmed (ie. error-free) audio outputs (eg. sound effects, music, dialogue) that are clustered according to features of the confirmed audio outputs (by eg. an unsupervised clustering algorithm), recei...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Pritpal Singh Panesar, Oliver George Hume, Lloyd Preston Stemple, Danjeli Schembri, Giacomo Costantini, Juuso Tolonen
Format:	Patent
Sprache:	eng
Schlagworte:	ACOUSTICS AMUSEMENTS CALCULATING CARD, BOARD, OR ROULETTE GAMES COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING GAMES GAMES NOT OTHERWISE PROVIDED FOR HUMAN NECESSITIES INDOOR GAMES USING SMALL MOVING PLAYING BODIES MUSICAL INSTRUMENTS PHYSICS SPEECH ANALYSIS OR SYNTHESIS SPEECH OR AUDIO CODING OR DECODING SPEECH OR VOICE PROCESSING SPEECH RECOGNITION SPORTS VIDEO GAMES
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	Errors in audio outputs during gameplay are detected by providing an audio output distribution of confirmed (ie. error-free) audio outputs (eg. sound effects, music, dialogue) that are clustered according to features of the confirmed audio outputs (by eg. an unsupervised clustering algorithm), receiving a sample audio output that occurs during gameplay, comparing the sample audio output to the audio output distribution (eg. the separation distance of the centre of the cluster), and detecting an error in the sample audio output when the sample audio output is inconsistent with the audio output distribution (via eg. a machine learning model). The erroneous waveform may then be highlighted, suppressed or deleted.