A Comparative Evaluation of Pitch Modification Techniques
This work addresses pitch modification in voice transformation systems, providing comparative insights for audio processing applications, but it is incremental as it builds on prior methods.
The paper compared four pitch modification techniques for voice transformation, finding that the Deterministic plus Stochastic Model (DSM) performed similarly or better than other methods for male speakers and large pitch modifications, but was outperformed by STRAIGHT for female voices.
This paper addresses the problem of pitch modification, as an important module for an efficient voice transformation system. The Deterministic plus Stochastic Model of the residual signal we proposed in a previous work is compared to TDPSOLA, HNM and STRAIGHT. The four methods are compared through an important subjective test. The influence of the speaker gender and of the pitch modification ratio is analyzed. Despite its higher compression level, the DSM technique is shown to give similar or better results than other methods, especially for male speakers and important ratios of modification. The DSM turns out to be only outperformed by STRAIGHT for female voices.