A Low-complexity Improved WI Speech Coding at 2kbps

The waveform interpolation (WI) speech coding presents a good performance at low bit rate. However, the algorithm has a very high complexity in computation. In this paper, a low-complexity improved waveform interpolation speech coder at 2kbps is proposed. The improved coding scheme has greatly reduced the computational complexity and improved the reconstructed speech quality by using various techniques, including FFT, cubic B-spline interpolation, nonlinear frequency resolution and so on. The algorithm complexity of the characteristic waveform (CW) representation and alignment is reduced from 43.3 to 9.2 MOPS. Furthermore, subjective listening tests show that the 2kb/s coder provides the high quality reconstructed speech.