Talking Condition Identification Using Second-Order Hidden Markov Models
This is an incremental improvement for speech processing applications, specifically enhancing talking condition identification.
The paper tackled the problem of identifying talking conditions (e.g., neutral, shouted, angry) in text- and speaker-dependent systems by using second-order hidden Markov models (HMM2s), resulting in significant performance improvement compared to first-order HMMs, though no concrete numbers are provided.
This work focuses on enhancing the performance of text-dependent and speaker-dependent talking condition identification systems using second-order hidden Markov models (HMM2s). Our results show that the talking condition identification performance based on HMM2s has been improved significantly compared to first-order hidden Markov models (HMM1s). Our talking conditions in this work are neutral, shouted, loud, angry, happy, and fear.