Search

The continuous monitoring and recording of food intake amount without user intervention is very useful in the prevention of obesity and metabolic diseases. I adopted a technique that automatically recognizes food intake amount by combining the identification of food types through image recognition and a technique that uses acoustic modality to recognize chewing events. The accuracy of using audio signal to detect eating activity is seriously degraded in a noisy environment. To alleviate this problem, contact sensing methods have conventionally been adopted, wherein sensors are attached to the face or neck region to reduce external noise. Such sensing methods, however, cause dermatological discomfort and a feeling of cosmetic unnaturalness for most users. In this study, a noise-robust and non-contact sensing method was employed, wherein ultrasonic Doppler shifts were used to detect chewing events. The experimental results showed that the mean absolute percentage errors (MAPEs) of an ultrasonic-based method were comparable with those of the audio-based method (15.3 vs. 14.6) when 30 food items were used for experiments. The food intake amounts were estimated for eight subjects in several noisy environments (cafeterias, restaurants, and home dining rooms). For all subjects, the estimation accuracy of the ultrasonic method was not degraded (the average MAPE was 15.02) even under noisy conditions. These results show that the proposed method has the potential to replace the manual logging method.

A large amount of parallel training corpus is necessary for robust, high-quality voice conversion. However, such parallel data may not always be available. This letter presents a new voice conversion method that needs no parallel speech corpus, and adopts a restricted Boltzmann machine (RBM) to represent the distribution of the spectral features derived from a target speaker. A linear transformation was employed to convert the spectral and delta features. A conversion function was obtained by maximizing the conditional probability density function with respect to the target RBM. A feasibility test was carried out on the OGI VOICES corpus. Results from the subjective listening tests and the objective results both showed that the proposed method outperforms the conventional GMM-based method.

A voice transformation (VT) method that can make the utterance of a source speaker mimic that of a target speaker is described. Speaker individuality transformation is achieved by altering three feature parameters, which include the LPC cepstrum, pitch period and gain. The main objective of this study involves construction of an optimal sequence of features selected from a target speaker’s database, to maximize both the correlation probabilities between the transformed and the source features and the likelihood of the transformed features with respect to the target model. A set of two-pass conversion rules is proposed, where the feature parameters are first selected from a database then the optimal sequence of the feature parameters is then constructed in the second pass. The conversion rules were developed using a statistical approach that employed a maximum likelihood criterion. In constructing an optimal sequence of the features, a hidden Markov model (HMM) was employed to find the most likely combination of the features with respect to the target speaker’s model. The effectiveness of the proposed transformation method was evaluated using objective tests and informal listening tests. We confirmed that the proposed method leads to perceptually more preferred results, compared with the conventional methods.

This letter describes a robust speech recognition system for recognizing fast speech by stretching the length of the utterance in the cepstrum domain. The degree of stretching for an utterance is determined by its rate of speech (ROS), which is based on a maximum likelihood (ML) criterion. The proposed method was evaluated on 10-digits mobile phone numbers. The results of the simulation show that the overall error rate was reduced by 17.8% when the proposed method was employed.

In text-to-speech synthesis, spectral smoothing is often employed to reduce artifacts at unit-joining points. A context-adaptive smoothing method is proposed in this letter, where the amount of smoothing is determined according to context information. Discontinuities at unit boundaries are predicted by a regression tree, and smoothing factors are computed by using predicted discontinuities and real discontinuities at unit boundaries. Experimental results are presented to demonstrate the effectiveness of the proposed method.

This letter addresses a temporal decomposition (TD) technique that is based on a rate-distortion criterion. In the proposed TD scheme, a set of interpolation functions is constructed from a given training corpus, and the optimum target points are found in the sense of minimizing, not only spectral distortion, but also bit rates. The results of the simulation show that an average spectral distortion of about 1.4 dB can be achieved at an average bit rate of about 8 bits/frame.