Bispectrum features for robust speaker identification

Along with the spoken message, speech contains information about the identity of the speaker. Thus, the goal of speaker identi cation is to develop features which are unique to each speaker. This paper explores a new feature for speech and shows how it can be used for robust speaker identi cation. The results will be compared to the cepstrum feature due to its widespread use and success in speaker identi cation applications. The cepstrum, however, has shown a lack of robustness in varying conditions, especially in a cross-condition environment where the classi er has been trained with clean data but then tested on corrupted data. Part of the bispectrum will be used as a new feature and we will demonstrate its usefulness in varying noise settings.