Yuichi Ishimoto

Comparative evaluations of robust and accurate F0 estimates in reverberant environments

This paper reports comparative evaluations of the method we previously proposed of estimating fundamental frequency (F0) based on complex cepstrum analysis with nine typical methods over huge speech-sound datasets in both artificial and realistic reverberant environments (in room acoustics). They involve several classic algorithms (Cepstrum, AMDF, TPC, and modified autocorrelation) and a few modern algorithms (TEMPO, YIN, and PHIA). The comparative results revealed that the percentage correct rates of the estimated FOs using them were drastically reduced as the reverberation time increased while Fo estimated with the proposed method was completely robust and accurate. They also demonstrated that homomorphic analysis and the concept of a source-filter model were relatively effective for estimating Fo. The results also demonstrated that it was much better than the previously reported methods in terms of robustness and providing accurate F0 estimates in both artificial and realistic reverberant environments.

Experimental investigation of end-of-utterance perception by final lowering in spontaneous Japanese

It is considered that final lowering, which is a phenomenon that the fundamental frequencies (F0s) fall significantly in sentence-final position, marks the end of an utterance in Japanese. However, it is not clear whether the hearer utilizes final lowering to recognize the end of the utterance. In this paper we investigated effect of final lowering on the perception of an end-of-utterance in spontaneous Japanese speech. We adopt a Bayesian hierarchical model to estimate final accentual phrases or utterance-final elements related to the end of the utterance from prosodic features. Results suggested that final lowering was associated with the syntactic elements mostly placed at the end of a Japanese utterance, but not with the end-of-utterance itself. We, then, carried out perceptual experiments using Japanese utterances with modified F0s either in the middle or at the end. The results showed that the subjects detected the end of the utterance even in the absence of final lowering and were not affected by the presence of an F0 downstep simulating the final lowering in the middle of the utterance. That suggests that Japanese hearers do not use final lowering to perceive the end of an utterance.

A study on prediction of end-of-utterance by prosodic features and phrase-dependency structure in spontaneous speech

This study is aimed at predicting the end of utterance by prosodic features and syntactic structure for spontaneous speech. In spontaneous everyday conversation, participants must predict the ends of utterances of a speaker to perform smooth turn-taking. We consider that they utilize not only syntactic factors but also prosodic factors for the end-of-utterance prediction because of the difficulty of prediction of a syntactic completion point in spontaneous Japanese speech. In previous studies, it was observed that prosodic factors changed such that the general fundamental frequency of utterance declined gradually toward the end of an utterance, and the intensity decreased significantly in the final accentual phrase. However, it is not clear what prosodic features support the prediction. We focused on dependency structure among bunsetsu-phrases as the syntactic factor and investigated the relation between the phrase-dependency and prosodic features based on a spontaneous Japanese conversation corpus. The r...

Acoustic features of speech after glossectomy

The tongue serves an important role in speech production. Speech disorders due to tongue resection often occur and cause communication difficulties after surgery, according to the extent of the resected area. Such patients typically require appropriate speech therapy and palatal augmentation prosthesis. However, diagnosis of the speech in such patients has been based largely on subjective evaluation by clinicians. Acoustic features in glossectomee have yet to be clarified, and there is no objective estimation method for speech intelligibility. This study aims to clarify acoustic features associated with speech disorders after glossectomy and to develop a computerized evaluation system. The speech data were analyzed using the improved cepstrum method and compared with varying degrees of speech intelligibility. The vowel /i/ was selected as the speech sample because it is the high front vowel. The results showed that spectral envelopes of the Japanese vowel /i/ with low speech intelligibility exhibit two pe...

Speech Enhancement and Segregation Based on Human Auditory Mechanisms

Humans can perceive specific desired sounds without difficulty, even in noisy environments. This is a useful ability that many animals possess, and is referred to as the ‘Cocktail party effect’. We believe that by modeling this mechanism we will be able to produce tools for speech enhancement and segregation, or for other problems in speech recognition and analysis.