Skip to main content

Table 1 GRU predictive model sample input and output dimensions for model training

From: Gated recurrent unit predictor model-based adaptive differential pulse code modulation speech decoder

\(\bar{x}(t)\)

x(t)

\(\bar{x}(t-1), \bar{x}(t-2), \bar{x}(t-3), \ldots , \bar{x}(t-p)\)

x(p)

\(\bar{x}(t-2), \bar{x}(t-3), \bar{x}(t-4), \ldots , \bar{x}(t-(p+1))\)

\(x(p+1)\)

\(\bar{x}(t-3), \bar{x}(t-4), \bar{x}(t-5), \ldots , \bar{x}(t-(p+2))\)

\(x(p+2)\)

\(\bar{x}(t-4), \bar{x}(t-5), \bar{x}(t-6), \ldots , \bar{x}(t-(p+3))\)

\(x(p+3)\)

\(\ldots\)

\(\ldots\)