Performance of phase-space voicing-state classification for Co-channel speech
This paper discusses the performance of a classification algorithm that is capable of determining the voicing-state of co-channel speech. The algorithm uses some features of the reconstructed phase-space of the speech data as a measure to identify the three voicing-states of co-channel speech; Unvoiced/Unvoiced (U/U), Voiced/Unvoiced (V/U), and Voiced/Voiced (V/V). The proposed method requires neither a priori information nor speech training data. Nonetheless, simulation results show enhanced performance in identifying the three voicing-states compared to other existing techniques. The algorithm also shows a reliable, performance for different SIR values as well as different levels of background noise.
|Keywords||Nonlinear speech processing, Phase-space reconstruction, Speech analysis, Speech signal processing, Time delay embedding, Voicing-state classification|
|Conference||IMTC'05 - Proceedings of the IEEE Instrumentation and Measurement Technology Conference|
Mahgoub, Y.A., & Dansereau, R. (2005). Performance of phase-space voicing-state classification for Co-channel speech. Presented at the IMTC'05 - Proceedings of the IEEE Instrumentation and Measurement Technology Conference.