Comparative Study of the Baum-Welch and Viterbi Training Algorithms Applied to Read and Spontaneous Speech Recognition

@inproceedings{RodrguezFuentes2003ComparativeSO,
  title={Comparative Study of the Baum-Welch and Viterbi Training Algorithms Applied to Read and Spontaneous Speech Recognition},
  author={Luis Javier Rodr{\'i}guez-Fuentes and M. In{\'e}s Torres},
  booktitle={IbPRIA},
  year={2003}
}
In this paper we compare the performance of acoustic HMMs obtained through Viterbi training with that of acoustic HMMs obtained through the Baum-Welch algorithm. We present recognition results for discrete and continuous HMMs, for read and spontaneous speech databases, acquired at 8 and 16 kHz. We also present results for a combination of Viterbi and Baum-Welch training, intended as a trade-off solution. Though Viterbi training yields a good performance in most cases, sometimes it leads to… CONTINUE READING