Malcolm SlaneyFollow


This publication describes methods of normalizing the speed of non-linear speech by applying an algorithm to allow for improved listener comprehension at increased playback speeds. The algorithm computes an amount of tension for a given audio file and subsequently computes a running average of the tension. A high-pass filter is then applied to the tension to remove the average tension. The resulting audio file allows a listener to increase playback speed or maintain a desired average speed while retaining comprehension.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.