Approaches are described for generating an audio signal that mimics speech captured a computing device. An input audio signal (e.g., a speech signal) can be transformed from the time domain into another domain, to generate one or more audio signal segments, where each segment can correspond to a window of time. The device can then determine, for each audio signal segment, a feature characteristic of the audio signal, such as a phoneme. Each one of segments can be mapped, based at least in part on the respective feature characteristic, to a model audio signal. The device can then generate an output audio signal including each model audio signal as determined by the mapping, where the output audio signal is in a sequence associated with the input audio signal.