Litcius/Paper detail

EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning

Jaeyeon Kim, Jae‐Yoon Jung, Jinjoo Lee, Sang Hoon Woo

202418 citationsDOI

Abstract

We propose EnCLAP, a novel framework for automated audio captioning. EnCLAP employs two acoustic representation models, EnCodec and CLAP, along with a pretrained language model, BART. We also introduce a new training objective called masked codec modeling that improves acoustic awareness of the pretrained language model. Experimental results on AudioCaps and Clotho demonstrate that our model surpasses the performance of baseline models. Source code will be available at https://github.com/jaeyeonkim99/EnCLAP. <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup>

Topics & Concepts

Computer scienceClosed captioningCodecEmbeddingSpeech recognitionSpeech codingLanguage modelSource codeNatural language processingCode (set theory)Artificial intelligenceProgramming languageComputer hardwareImage (mathematics)Set (abstract data type)Music and Audio ProcessingSpeech Recognition and SynthesisSpeech and Audio Processing
EnCLAP: Combining Neural Audio Codec and Audio-Text Joint Embedding for Automated Audio Captioning | Litcius