Recognition of unvoiced stops from their time-frequency representation

The recognition of the unvoiced stop sounds /k/, /p/ and /t/ in a speech signal is an interesting problem, due to the irregular, aperiodic, nonstationary nature of the corresponding signals. Their spotting is much easier, however, thanks to the characteristic silence interval they include. Classification of these three phonemes is proposed, based on the patterns extracted from their time-frequency representation. This is possible because the different articulation points of /k/, /p/ and /t/ are reflected into distinct patterns of evolution of their spectral contents with time. These patterns can be obtained by suitable time-frequency analysis, and then used for classification. The Wigner distribution of the unvoiced stop signals, appropriately smoothed and subsampled, is proposed as the basic classification pattern. Finally, for the classification step, the learning vector quantization (LVQ) classifier of Kohonen (1988) is employed on a set of unvoiced stop signals extracted from the TIMIT speech database, with encouraging results under context- and speaker-independent testing conditions