2016
DOI: 10.1109/tcds.2016.2550591
|View full text |Cite
|
Sign up to set email alerts
|

Nonparametric Bayesian Double Articulation Analyzer for Direct Language Acquisition From Continuous Speech Signals

Abstract: Human infants can discover words directly from unsegmented speech signals without any explicitly labeled data. The main problem of this paper is to develop a computational model that can estimate language and acoustic models, and discover words directly from continuous human speech signals in an unsupervised manner. For this purpose, we propose an integrative generative model that combines a language model and an acoustic model into a single generative model called the "hierarchical Dirichlet process hidden la… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
60
0

Year Published

2016
2016
2023
2023

Publication Types

Select...
6
1

Relationship

2
5

Authors

Journals

citations
Cited by 30 publications
(60 citation statements)
references
References 44 publications
(73 reference statements)
0
60
0
Order By: Relevance
“…Hierarchical Dirichlet process hidden language model (HDP-HLM) is a probabilistic generative model that models double articulation structure (i.e., two-layer hierarchy, a characteristic of human spoken language) (Taniguchi et al, 2016b). Mathematically, HDP-HLM is a natural extension of hierarchical Dirichlet process hidden semi-Markov model (HDP-HSMM), which is a type of generalization of hidden Markov model (Johnson and Willsky, 2013).…”
Section: Npb-daamentioning
confidence: 99%
See 3 more Smart Citations
“…Hierarchical Dirichlet process hidden language model (HDP-HLM) is a probabilistic generative model that models double articulation structure (i.e., two-layer hierarchy, a characteristic of human spoken language) (Taniguchi et al, 2016b). Mathematically, HDP-HLM is a natural extension of hierarchical Dirichlet process hidden semi-Markov model (HDP-HSMM), which is a type of generalization of hidden Markov model (Johnson and Willsky, 2013).…”
Section: Npb-daamentioning
confidence: 99%
“…An inference procedure for HDP-HLM was proposed in (Taniguchi et al, 2016b). This procedure is based on the blocked Gibbs sampler for HDP-HSMM proposed by Johnson (Johnson and Willsky, 2013).…”
Section: Npb-daamentioning
confidence: 99%
See 2 more Smart Citations
“…To segment such data, extraction of temporal patterns in an unsupervised manner is necessary. This has become an active topic in several research fields, such as health care (Zeger et al, 2006), biology (Saeedi et al, 2016), speech recognition (Taniguchi et al, 2016), natural language processing (Heller et al, 2009), and motion analysis (Barbič et al, 2004). Although many methods have been proposed to extract temporal patterns (Keogh et al, 2004), there exists a problem that the number of existing patterns (and consequently, the number of segments) is generally unknown beforehand.…”
Section: Introductionmentioning
confidence: 99%