This paper gives a general overview of techniques in statistical parametric speech synthesis. One of the instances of these techniques, called HMM-based generation synthesis (or simply HMM-based synthesis), has recently been shown to be very effective in generating acceptable speech synthesis. This paper also contrasts these techniques with the more conventional unit selection technology that has dominated speech synthesis over the last ten years. Advantages and disadvantages of statistical parametric synthesis are highlighted as well as identifying where we expect the key developments to appear in the immediate future.

https://www.sp.nitech.ac.jp/~bonanza/Paper/EMIME/zen_specom.pdf

Statistical Parametric Speech Synthesis

A new kernel function between two labeled graphs is presented. Feature vectors are defined as the counts of label paths produced by random walks on graphs. The kernel computation finally boils down to obtaining the stationary state of a discrete-time linear system, thus is efficiently performed by solving simultaneous linear equations. Our kernel is based on an infinite dimensional feature space, so it is fundamentally different from other string or tree kernels based on dynamic programming. We will present promising empirical results in classification of chemical compounds.

/pdf/marginalized-kernels-between-labeled-graphs-1lfid2nyzm.pdf

Marginalized kernels between labeled graphs

The literature on short-term traffic flow forecasting has undergone great development recently. Many works, describing a wide variety of different approaches, which very often share similar features and ideas, have been published. However, publications presenting new prediction algorithms usually employ different settings, data sets, and performance measurements, making it difficult to infer a clear picture of the advantages and limitations of each model. The aim of this paper is twofold. First, we review existing approaches to short-term traffic flow forecasting methods under the common view of probabilistic graphical models, presenting an extensive experimental comparison, which proposes a common baseline for their performance analysis and provides the infrastructure to operate on a publicly available data set. Second, we present two new support vector regression models, which are specifically devised to benefit from typical traffic flow seasonality and are shown to represent an interesting compromise between prediction accuracy and computational efficiency. The SARIMA model coupled with a Kalman filter is the most accurate model; however, the proposed seasonal support vector regressor turns out to be highly competitive when performing forecasts during the most congested periods.

Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning

https://hal.archives-ouvertes.fr/hal-00499180/document

Automatic speech recognition and speech variability: A review

This paper gives a general overview of hidden Markov model (HMM)-based speech synthesis, which has recently been demonstrated to be very effective in synthesizing speech. The main advantage of this approach is its flexibility in changing speaker identities, emotions, and speaking styles. This paper also discusses the relation between the HMM-based approach and the more conventional unit-selection approach that has dominated over the last decades. Finally, advanced techniques for future developments are described.

/pdf/speech-synthesis-based-on-hidden-markov-models-45y6v1rk5u.pdf

Speech Synthesis Based on Hidden Markov Models

A new class of Support Vector Machine (SVM) that is applicable to sequential-pattern recognition such as speech recognition is developed by incorporating an idea of non-linear time alignment into the kernel function. Since the time-alignment operation of sequential pattern is embedded in the new kernel function, standard SVM training and classification algorithms can be employed without further modifications. The proposed SVM (DTAK-SVM) is evaluated in speaker-dependent speech recognition experiments of hand-segmented phoneme recognition. Preliminary experimental results show comparable recognition performance with hidden Markov models (HMMs).

/pdf/dynamic-time-alignment-kernel-in-support-vector-machine-5avzhgwcvo.pdf

Dynamic Time-Alignment Kernel in Support Vector Machine

A new method is proposed for online handwriting recognition of Kanji characters. The method employs substroke HMM as minimum units to constitute Japanese Kanji characters and utilizes the direction of pen motion. The main motivation is to fully utilize the continuous speech recognition algorithm by relating sentence speech to Kanji character phonemes to substrokes, and grammar to Kanji structure. The proposed system consists input feature analysis, substroke HMM, a character structure dictionary and a decoder. The present approach has the following advantages over the conventional methods that employ whole character HMM. 1) Much smaller memory requirement for dictionary and models. 2) Fast recognition by employing efficient substroke network search. 3) Capability of recognizing characters not included in the training data if defined as a sequence of substrokes in the dictionary. 4) Capability of recognizing characters written by various different stroke orders with multiple definitions per one character in the dictionary. 5) Easiness in HMM adaptation to the user with a few sample character data.

/pdf/substroke-approach-to-hmm-based-on-line-kanji-handwriting-4zrac81ley.pdf

Substroke approach to HMM-based on-line Kanji handwriting recognition

Proposes a class of hidden Markov model (HMM) called multiple-regression HMM (MR-HMM) that utilizes auxiliary features such as fundamental frequency (F/sub 0/) and speaking styles that affect spectral parameters to better model the acoustic features of phonemes. Though such auxiliary features are considered to be the factors that degrade the performance of speech recognizers, the proposed MR-HMM adapts its model parameters, i.e. mean vectors of output probability distributions, depending on these auxiliary information to improve the recognition accuracy. Formulation for parameter reestimation of MR-HMM based on the EM algorithm is given in the paper. Experiments of speaker-dependent isolated word recognition demonstrated that MR-HMMs using F/sub 0/ based auxiliary features reduced the error rates by more than 20% compared with the conventional HMMs.

/pdf/multiple-regression-hidden-markov-model-2otfnwu8i2.pdf

Multiple-regression hidden Markov model

Support vector machine with dynamic time-alignment kernel for speech recognition.

Describes context-dependent substroke hidden Markov models (HMMs)for on-line handwritten recognition of cursive Kanji and Hiragana characters. In order to tackle this problem, we have proposed the substroke HMM approach where a modeling unit "substroke" that is much smaller than a whole character is employed and each character is modeled as a concatenation of only 25 kinds of substroke HMMs. One of the drawbacks of this approach is that the recognition accuracy deteriorates in the case of scribbled characters, and characters where the shape of the substrokes varies a lot. We show that the context-dependent substroke modeling which depends on how the substroke connects to the adjacent substrokes is effective for achieving robust recognition of low quality characters, The successive state splitting algorithm which was mainly developed for speech recognition is employed to construct the context dependent substroke HMMs. Experimental results show that the correct recognition rate improved from 88% to 92% for cursive Kanji handwriting and from 90% to 98% for Hiragana handwriting.

/pdf/context-dependent-substroke-model-for-hmm-based-on-line-3w1ofzhsus.pdf

Mitsuru Nakai

Papers

Dynamic Time-Alignment Kernel in Support Vector Machine

Substroke approach to HMM-based on-line Kanji handwriting recognition

Multiple-regression hidden Markov model

Support vector machine with dynamic time-alignment kernel for speech recognition.

Context-dependent substroke model for HMM-based on-line handwriting recognition