← Search

Teerapat Jenrungrot

2 accepted papers

2023

LMCodec: A Low Bitrate Speech Codec with Causal Transformer Models

ICASSP 2023accepted

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…

Cited by 0SourceScholar
2020

The Cone of Silence: Speech Separation by Localization

NeurIPS 2020oral

Given a multi-microphone recording of an unknown number of speakers talking concurrently, we simultaneously localize the sources and separate the individual speakers. At the core of our method is a deep network, in the waveform domain, which isolates sources within an angular region $\theta \pm w/2$…