Ryo Ozaki

Akira Taniguchi, Hiroaki Murakami, Ryo Ozaki et al.

Human infants acquire their verbal lexicon with minimal prior knowledge of language based on the statistical properties of phonological distributions and the co-occurrence of other sensory stimuli. This study proposes a novel fully unsupervised learning method for discovering speech units using phonological information as a distributional cue and object information as a co-occurrence cue. The proposed method can acquire words and phonemes from speech signals using unsupervised learning and utilize object information based on multiple modalities-vision, tactile, and auditory-simultaneously. The proposed method is based on the nonparametric Bayesian double articulation analyzer (NPB-DAA) discovering phonemes and words from phonological features, and multimodal latent Dirichlet allocation (MLDA) categorizing multimodal information obtained from objects. In an experiment, the proposed method showed higher word discovery performance than baseline methods. Words that expressed the characteristics of objects (i.e., words corresponding to nouns and adjectives) were segmented accurately. Furthermore, we examined how learning performance is affected by differences in the importance of linguistic information. Increasing the weight of the word modality further improved performance relative to that of the fixed condition.

Asuka Moritani, Ryo Ozaki, Shoki Sakamoto et al.

This paper shows that StarGAN-VC, a spectral envelope transformation method for non-parallel many-to-many voice conversion (VC), is capable of emotional VC (EVC). Although StarGAN-VC has been shown to enable speaker identity conversion, its capability for EVC for Japanese phrases has not been clarified. In this paper, we describe the direct application of StarGAN-VC to an EVC task with minimal fundamental frequency and aperiodicity processing. Through subjective evaluation experiments, we evaluated the performance of our StarGAN-EVC system in terms of its ability to achieve EVC for Japanese phrases. The subjective evaluation is conducted in terms of subjective classification and mean opinion score of neutrality and similarity. In addition, the interdependence between the source and target emotional domains was investigated from the perspective of the quality of EVC.

Yasuaki Okuda, Ryo Ozaki, Tadahiro Taniguchi

Infants acquire words and phonemes from unsegmented speech signals using segmentation cues, such as distributional, prosodic, and co-occurrence cues. Many pre-existing computational models that represent the process tend to focus on distributional or prosodic cues. This paper proposes a nonparametric Bayesian probabilistic generative model called the prosodic hierarchical Dirichlet process-hidden language model (Prosodic HDP-HLM). Prosodic HDP-HLM, an extension of HDP-HLM, considers both prosodic and distributional cues within a single integrative generative model. We conducted three experiments on different types of datasets, and demonstrate the validity of the proposed method. The results show that the Prosodic DAA successfully uses prosodic cues and outperforms a method that solely uses distributional cues. The main contributions of this study are as follows: 1) We develop a probabilistic generative model for time series data including prosody that potentially has a double articulation structure; 2) We propose the Prosodic DAA by deriving the inference procedure for Prosodic HDP-HLM and show that Prosodic DAA can discover words directly from continuous human speech signals using statistical information and prosodic information in an unsupervised manner; 3) We show that prosodic cues contribute to word segmentation more in naturally distributed case words, i.e., they follow Zipf's law.

Ryo Nakashima, Ryo Ozaki, Tadahiro Taniguchi

This paper describes a new unsupervised machine learning method for simultaneous phoneme and word discovery from multiple speakers. Human infants can acquire knowledge of phonemes and words from interactions with his/her mother as well as with others surrounding him/her. From a computational perspective, phoneme and word discovery from multiple speakers is a more challenging problem than that from one speaker because the speech signals from different speakers exhibit different acoustic features. This paper proposes an unsupervised phoneme and word discovery method that simultaneously uses nonparametric Bayesian double articulation analyzer (NPB-DAA) and deep sparse autoencoder with parametric bias in hidden layer (DSAE-PBHL). We assume that an infant can recognize and distinguish speakers based on certain other features, e.g., visual face recognition. DSAE-PBHL is aimed to be able to subtract speaker-dependent acoustic features and extract speaker-independent features. An experiment demonstrated that DSAE-PBHL can subtract distributed representations of acoustic signals, enabling extraction based on the types of phonemes rather than on the speakers. Another experiment demonstrated that a combination of NPB-DAA and DSAE-PB outperformed the available methods in phoneme and word discovery tasks involving speech signals with Japanese vowel sequences from multiple speakers.