Yasunaga Miyazawa, Jun-ichi Takami, Shigeki Sagayama, Shoichi Matsunaga. All-phoneme ergodic hidden Markov network for unsupervised speaker adaptation. In Proceedings of ICASSP '94: IEEE International Conference on Acoustics, Speech and Signal Processing, Adelaide, South Australia, Australia, April 19-22, 1994. pages 249-252, IEEE Computer Society, 1994. [doi]
Abstract is missing.