Litcius/Paper detail

Text-to-Audio Grounding: Building Correspondence Between Captions and Sound Events

Xuenan Xu, Heinrich Dinkel, Mengyue Wu, Kai Yu

202122 citationsDOI

Abstract

Automated Audio Captioning is a cross-modal task, generating natural language descriptions to summarize the audio clips’ sound events. However, grounding the actual sound events in the given audio based on its corresponding caption has not been investigated. This paper contributes an Audio-Grounding dataset <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> , which provides the correspondence be-tween sound events and the captions provided in Audiocaps, along with the location (timestamps) of each present sound event. Based on such, we propose the text-to-audio grounding (TAG) task, which interactively considers the relationship be-tween audio processing and language understanding. A base-line approach is provided, resulting in an event-F1 score of 28.3% and a Polyphonic Sound Detection Score (PSDS) score of 14.7%.

Topics & Concepts

Computer scienceClosed captioningEvent (particle physics)TimestampPolyphonySpeech recognitionTask (project management)Audio signal processingSound (geography)Audio analyzerNatural language processingAudio signalSound recording and reproductionArtificial intelligenceAcousticsSpeech codingEngineeringReal-time computingImage (mathematics)Systems engineeringPhysicsQuantum mechanicsMusic and Audio ProcessingSpeech and Audio ProcessingSpeech Recognition and Synthesis