LMCodec: A Low Bitrate Speech Codec With Causal Transformer Models

Autor:	Jenrungrot, Teerapat, Chinen, Michael, Kleijn, W. Bastiaan, Skoglund, Jan, Borsos, Zalán, Zeghidour, Neil, Tagliasacchi, Marco
Rok vydání:	2023
Předmět:	Computer Science - Sound Electrical Engineering and Systems Science - Audio and Speech Processing
Druh dokumentu:	Working Paper
Popis:	We introduce LMCodec, a causal neural speech codec that provides high quality audio at very low bitrates. The backbone of the system is a causal convolutional codec that encodes audio into a hierarchy of coarse-to-fine tokens using residual vector quantization. LMCodec trains a Transformer language model to predict the fine tokens from the coarse ones in a generative fashion, allowing for the transmission of fewer codes. A second Transformer predicts the uncertainty of the next codes given the past transmitted codes, and is used to perform conditional entropy coding. A MUSHRA subjective test was conducted and shows that the quality is comparable to reference codecs at higher bitrates. Example audio is available at https://mjenrungrot.github.io/chrome-media-audio-papers/publications/lmcodec. Comment: 5 pages, accepted to ICASSP 2023, project page: https://mjenrungrot.github.io/chrome-media-audio-papers/publications/lmcodec
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2303.12984 Zobrazit plný text záznamu View this record from Arxiv