Date:
Fri, 02/07/2020 - 10:30am - 12:00pm
Location:
CCRMA Seminar Room
Event Type:
Hearing Seminar
In recent years, deep generative models like SampleRNN and WaveNet have shown a remarkable ability to generate realistic-sounding speech. One application of these models has been to the problem of low-bitrate speech coding. We will discuss our recent work “High-Quality Speech Coding with SampleRNN" (published in ICASSP 2019), where we demonstrate that speech can be coded at high quality using much lower bitrates than previously possible. We will describe the strengths and limitations of the proposed scheme, as well as some follow-up work.
This is work that was done in collaboration with Janusz Klejsa, Per Hedelin, and Lars Villemoes of the Dolby Sweden office.
Who: Roy Fejgin and Cong Zhou (Dolby)
