Idioma:

Structure Learning of Continuous Speech based Unsupervised Segmentation

Nagano, Masatoshi ; Nakamura, Tomoaki

Journal of the Robotics Society of Japan, 2023, Vol.41(3), pp.318-321

Sem texto completo

Citações Citado por

Título:
Structure Learning of Continuous Speech based Unsupervised Segmentation
Autor: Nagano, Masatoshi ; Nakamura, Tomoaki
Assuntos: GP-HSMM ; Segmentation ; Serket ; Unsupervised Learning
É parte de: Journal of the Robotics Society of Japan, 2023, Vol.41(3), pp.318-321
Descrição: Humans can divide perceived continuous speech signals into phonemes and words, which have a double articulation structure, without explicit boundary points and labels, and learn the language. Learning such a double articulation structure of speech signals is important for realizing a robot that can acquire vocabulary and have a conversation. In this paper, we propose a novel statistical model GP-HSMM-DAA (Gaussian Process Hidden Semi Markov Model-based Double Articulation Analyzer) that can learn double articulation structures of time-series data by connecting statistical models hierarchically. In the proposed model, the parameters of each statistical model are mutually updated and learned complementarily. We present that GP-HSMM-DAA can segment continuous speech into phonemes and words with higher accuracy than the baseline methods.
Editor: The Robotics Society of Japan
Idioma: Japonês;Inglês

Voltar para lista de resultados