State Duration Modeling Research Articles

EpiSegMix: a flexible distribution hidden Markov model with duration modeling for chromatin state discovery.

Automated chromatin segmentation based on ChIP-seq (chromatin immunoprecipitation followed by sequencing) data reveals insights into the epigenetic regulation of chromatin accessibility. Existing segmentation methods are constrained by simplifying modeling assumptions, which may have a negative impact on the segmentation quality. We introduce EpiSegMix, a novel segmentation method based on a hidden Markov model with flexible read count distribution types and state duration modeling, allowing for a more flexible modeling of both histone signals and segment lengths. In a comparison with existing tools, ChromHMM, Segway, and EpiCSeg, we show that EpiSegMix is more predictive of cell biology, such as gene expression. Its flexible framework enables it to fit an accurate probabilistic model, which has the potential to increase the biological interpretability of chromatin states. Source code: https://gitlab.com/rahmannlab/episegmix.

A State Duration Model for Brand Choice and Inter-Purchase Time

A new approach for analyzing state duration data in brand-choice studies is explored. This approach not only incorporates the correlation among repeated purchases for a subject, it also models the purchase timing and the brand decision jointly. The former is accomplished by applying transition model approaches from longitudinal studies while the latter is done by conditioning on the brand choice variable. Then mixed multinomial logit models and Cox proportional hazards models are employed to model the marginal densities of the brand choice and the conditional densities of the interpurchase time given the brand choice. We illustrate the approach using a Nielsen household scanner panel data set

Bird Species Recognition Using Unsupervised Modeling of Individual Vocalization Elements

This paper investigates acoustic modeling for recognition of bird species from audio field recordings. First, the acoustic scene is decomposed into isolated segments, corresponding to detected sinusoids. Each segment is represented by a sequence of the frequency and normalized magnitude values of the sinusoid. The temporal evolution of these features is modeled using hidden Markov models HMMs. A novel method for an unsupervised modeling of individual bird vocalization elements is proposed. The element models are initialized using HMM-based clustering and then further trained using an iterative maximum likelihood label re-assignment procedure. State duration modeling, performed in a post-recognition stage, is explored. Finally, we developed a hybrid deep neural network—hidden Markov model. The developed acoustic models are employed for bird species identification, detection of specific species, and recognition of multiple bird species vocalizing in a given recording. The detection system employs score normalization. Recognition of multiple bird species is performed based on maximizing the likelihood of a set of segments on a subset of bird species models, with penalization based on Bayesian information criterion applied. Experimental evaluations are performed on more than 37 h of sound field recordings, containing vocalizations of 48 bird species, plus more than 16 h of non-bird sound recordings. Using 3 s of the detected signal, the best system achieved: identification accuracy of 98.7%, detection with the equal error rate of 2.7%, and recognition accuracy of 97.3% and 95.4% when vocalizations of multiple bird species are present, with the number of bird species known and estimated, respectively.

State duration and interval modeling in hidden semi-Markov model for sequential data analysis

Sequential data modeling and analysis have become indispensable tools for analyzing sequential data, such as time-series data, because larger amounts of sensed event data have become available. These methods capture the sequential structure of data of interest, such as input-output relations and correlation among datasets. However, because most studies in this area are specialized or limited to their respective applications, rigorous requirement analysis of such models has not been undertaken from a general perspective. Therefore, we particularly examine the structure of sequential data, and extract the necessity of `state duration' and `state interval' of events for efficient and rich representation of sequential data. Specifically addressing the hidden semi-Markov model (HSMM) that represents such state duration inside a model, we attempt to add representational capability of a state interval of events onto HSMM. To this end, we propose two extended models: an interval state hidden semi-Markov model (IS-HSMM) to express the length of a state interval with a special state node designated as "interval state node"; and an interval length probability hidden semi-Markov model (ILP-HSMM) which represents the length of the state interval with a new probabilistic parameter "interval length probability." Exhaustive simulations have revealed superior performance of the proposed models in comparison with HSMM. These proposed models are the first reported extensions of HMM to support state interval representation as well as state duration representation.

Spatiotemporal radar target identification using radar cross-section modeling and hidden Markov models

We propose a target identification scheme exploiting the temporal dependency and spatial structure of radar cross-section (RCS) measurements in low-frequency, passive, or long-range surveillance radar systems. We employ target RCS modeling integrated into a hidden Markov model (HMM) with state-duration modeling. Assuming that the radar system ensures a sufficient sampling time, it is possible to use the spatial characteristics of airborne targets, because there is consistency between successively sampled RCS measurements. In addition, to exploit the whole temporal characteristic of the sequence of RCS measurements,which has rarely been considered in the literature, we adopt the HMM and target RCS modeling. To accomplish this task, we accurately develop target RCS models and establish the relationship between the target-sensor orientations, which are the hidden states of the HMM, and the correspondingRCSmeasurements. The proposed target identification scheme, which only uses the sequence of RCS measurements, is demonstrated with simulation results and an analysis for various signal-to-noise ratios and target-fluctuation models.

Automatic detection of volcano-seismic events by modeling state and event duration in hidden Markov models

In this paper we propose an automatic volcano event detection system based on Hidden Markov Model (HMM) with state and event duration models. Since different volcanic events have different durations, therefore the state and whole event durations learnt from the training data are enforced on the corresponding state and event duration models within the HMM. Seismic signals from the Llaima volcano are used to train the system. Two types of events are employed in this study, Long Period (LP) and Volcano-Tectonic (VT). Experiments show that the standard HMMs can detect the volcano events with high accuracy but generates false positives. The results presented in this paper show that the incorporation of duration modeling can lead to reductions in false positive rate in event detection as high as 31% with a true positive accuracy equal to 94%. Further evaluation of the false positives indicate that the false alarms generated by the system were mostly potential events based on the signal-to-noise ratio criteria recommended by a volcano expert.

Intelligibility of time-compressed synthetic speech: Compression method and speaking style

We present a series of intelligibility experiments performed on natural and synthetic speech time-compressed at a range of rates and analyze the effect of speech corpus and compression method on the intelligibility scores of sighted and blind individuals. Particularly we are interested in comparing linear and non-linear compression methods applied to normal and fast speech of different speakers. We recorded English and German language voice talents reading prompts at a normal and a fast rate. To create synthetic voices we trained a statistical parametric speech synthesis system based on the normal and the fast data of each speaker. We compared three compression methods: scaling the variance of the state duration model, interpolating the duration models of the fast and the normal voices, and applying a linear compression method to the generated speech waveform. Word recognition results for the English voices show that generating speech at a normal speaking rate and then applying linear compression resulted in the most intelligible speech at all tested rates. A similar result was found when evaluating the intelligibility of the natural speech corpus. For the German voices, interpolation was found to be better at moderate speaking rates but the linear method was again more successful at very high rates, particularly when applied to the fast data. Phonemic level annotation of the normal and fast databases showed that the German speaker was able to reproduce speech at a fast rate with fewer deletion and substitution errors compared to the English speaker, supporting the intelligibility benefits observed when compressing his fast speech. This shows that the use of fast speech data to create faster synthetic voices does not necessarily lead to more intelligible voices as results are highly dependent on how successful the speaker was at speaking fast while maintaining intelligibility. Linear compression applied to normal rate speech can more reliably provide higher intelligibility, particularly at ultra fast rates.

Learning multimodal behavioral models for face-to-face social interaction

The aim of this paper is to model multimodal perception-action loops of human behavior in face-to-face interactions. To this end, we propose trainable behavioral models that predict the optimal actions for one specific person given others’ perceived actions and the joint goals of the interlocutors. We first compare sequential models—in particular discrete hidden Markov models (DHMMs)—with standard classifiers (SVMs and decision trees). We propose a modification of the initialization of the DHMMs in order to better capture the recurrent structure of the sensory-motor states. We show that the explicit state duration modeling by discrete hidden semi markov models (DHSMMs) improves prediction performance. We applied these models to parallel speech and gaze data collected from interacting dyads. The challenge was to predict the gaze of one subject given the gaze of the interlocutor and the voice activity of both. For both DHMMs and DHSMMs the short-time Viterbi concept is used for incremental decoding and prediction. For the proposed models we evaluated objectively several properties in order to go beyond pure classification performance. Results show that incremental DHMMs (IDHMMs) were more efficient than classic classifiers and superseded by incremental DHSMMs (IDHSMMs). This later result emphasizes the relevance of state duration modeling.

Semi-continuous HMMs with explicit state duration for unconstrained Arabic word modeling and recognition

In this paper, we describe an off-line unconstrained handwritten Arabic word recognition system based on segmentation-free approach and semi-continuous hidden Markov models (SCHMMs) with explicit state duration. Character durations play a significant part in the recognition of cursive handwriting. The duration information is still mostly disregarded in HMM-based automatic cursive handwriting recognizers due to the fact that HMMs are deficient in modeling character durations properly. We will show experimentally that explicit state duration modeling in the SCHMM framework can significantly improve the discriminating capacity of the SCHMMs to deal with very difficult pattern recognition tasks such as unconstrained handwritten Arabic recognition. In order to carry out the letter and word model training and recognition more efficiently, we propose a new version of the Viterbi algorithm taking into account explicit state duration modeling. Three distributions (Gamma, Gauss and Poisson) for the explicit state duration modeling have been used and a comparison between them has been reported. To perform word recognition, the described system uses an original sliding window approach based on vertical projection histogram analysis of the word and extracts a new pertinent set of statistical and structural features from the word image. Several experiments have been performed using the IFN/ENIT benchmark database and the best recognition performances achieved by our system outperform those reported recently on the same database.

Arabic Handwritten Word Recognition Using HMMs with Explicit State Duration

We describe an offline unconstrained Arabic handwritten word recognition system based on segmentation-free approach and discrete hidden Markov models (HMMs) with explicit state duration. Character durations play a significant part in the recognition of cursive handwriting. The duration information is still mostly disregarded in HMM-based automatic cursive handwriting recognizers due to the fact that HMMs are deficient in modeling character durations properly. We will show experimentally that explicit state duration modeling in the HMM framework can significantly improve the discriminating capacity of the HMMs to deal with very difficult pattern recognition tasks such as unconstrained Arabic handwriting recognition. In order to carry out the letter and word model training and recognition more efficiently, we propose a new version of the Viterbi algorithm taking into account explicit state duration modeling. Three distributions (Gamma, Gauss, and Poisson) for the explicit state duration modeling have been used, and a comparison between them has been reported. To perform word recognition, the described system uses an original sliding window approach based on vertical projection histogram analysis of the word and extracts a new pertinent set of statistical and structural features from the word image. Several experiments have been performed using the IFN/ENIT benchmark database and the best recognition performances achieved by our system outperform those reported recently on the same database.

State Duration Modeling for HMM-Based Speech Synthesis

This paper describes the explicit modeling of a state duration's probability density function in HMM-based speech synthesis. We redefine, in a statistically correct manner, the probability of staying in a state for a time interval used to obtain the state duration PDF and demonstrate improvements in the duration of synthesized speech.

Estimating tonal prosodic discontinuities in Spanish using HMM

The tonal prosodic discontinuity estimation in Spanish is exhaustively modelled using HMM. Due to the high morphological complexity in Spanish, a relatively coarse grammatical categorization is tested in two sorts of texts (sentences from newspapers and a theatre play). The estimation of the type of discontinuity (falling or rising tones) at the boundary of intonation groups is assessed. The HMM approach is tested with: (a) modelling the observation probability with monograms, bigrams and full-window probability; (b) state duration modelling; (c) discriminative analysis of intermediate and final observation vectors and (d) penalization scheme in Viterbi decoding. The optimal configurations led to reductions of 3% or 5% in error detection. The estimation of the observation probability with monograms and bigrams leads to worse results than the ordinary full-window probability, although they provide better generalization. Nevertheless, the performance of the monograms and bigrams approximation can be enhanced if applied in combination with state duration constraints.

Context-Dependent Phoneme Duration Modeling with Tree-Based State Tying

This letter presents two methods of modeling phoneme durations. One is the context-independent phoneme duration modeling in which duration parameters are stored in each phoneme. The other is the context-dependent duration modeling in which duration parameters are stored in each state shared by context-dependent phonemes. The phoneme duration model is compared with a without-duration model and a state duration model. Experiments are performed on a database collected over the telephone network. Experimental results show that duration information rejects out-of-task (OOT) words well and that the context-dependent duration model yields the best performance among the tested models.

Packet-loss modelling in IP networks with state-duration constraints

A Gilbert–gamma topology is proposed to model packet-loss processes in UDP connections. The proposed topology introduces state duration modelling with gamma distributions. When compared with the ordinary Gilbert model the proposed topology substantially improves the likelihood of observed packet-loss processes, and gives reductions as high as 70% in the subjective estimation of speech quality transmitted over IP networks. The results presented can be easily applied to other real-time applications such as audio and video streaming.

Robust speaker verification with state duration modeling

This paper addresses the problem of state duration modeling in the Viterbi algorithm in a text-dependent speaker verification task. The results presented in this paper suggest that temporal constraints can lead to reductions of 10% and 20% in the error rates with signals corrupted by noise at SNR equal to 6 and 0 dB, respectively, and that the accurate statistical modeling of state duration (e.g. with gamma probability distribution) does not seem to be very relevant if maximal and minimal state duration restrictions are imposed. In contrast, temporal restrictions do not seem to give any improvement in a speaker verification task with clean speech or high SNR. It is also shown that state duration constraints can easily be applied with the likelihood normalization metrics based on speaker-dependent temporal parameters. Finally, the results here presented show that word position-dependent state duration parameters give no significant improvement when compared with the word position-independent approach if the coarticulation effect between contiguous words is low.

State duration models in clinical and observational studies.

Many studies in medicine involve conditions whereby subjects make transitions among a set of defined states over time. In such situations the durations of sojourns in specific states is frequently of interest. This article considers the modelling and analysis of sojourn times, beginning with semi-Markov models in which the durations of different sojourns are independent, and then considering extended models incorporating chronological time effects and random effects. Methodologic challenges for inference are discussed, and examples involving a relapse-remitting process and recurrent events are considered.

Improvement of noisy speech recognition using a proportional alignment decoding algorithm in the training phase

Modelling the state duration of hidden Markov models (HMMs) can effectively improve the accuracy in decoding the state sequence of an utterance and result in an improvement of speech recognition accuracy. However, when a speech signal is contaminated by ambient noise, the decoded state sequence may be distorted. It may stay at some states too long or too short even with the help of state duration models. This paper presents a proportional alignment decoding (PAD) algorithm for retraining the HMMs. A task of multi-speaker isolated Mandarin digit recognition was conducted to demonstrate the effectiveness and robustness of the PAD-based variable duration hidden Markov model (VDHMM/PAD) method. Experimental results show that the discriminativity of VDHMM/PAD in a noisy environment has been significantly enhanced. Moreover, the proposed method outperforms those widely used state duration modelling methods, such as using Poisson, gamma, Gaussian, bounded and non-parametric probability density functions.

Robust parametric modeling of durations in hidden Markov models

A major weakness of conventional hidden Markov models is that they implicitly model state durations by a geometric distribution, which is usually inappropriate. This paper presents a modified Viterbi algorithm that, by incorporating proper state and word duration modeling, significantly reduces the string error rate of the conventional Viterbi algorithm for a speaker-independent, connected-digit string task. The algorithm has essentially the same computational requirements of the conventional Viterbi algorithm.

Nonstationary hidden Markov model

The standard hidden Markov model (HMM) has often been pointed out for its inappropriateness in capturing state duration behavior. Explicit state duration modeling in the HMM has been developed but it is not sufficient for modeling the intrinsically dynamic, or nonstationary, transition process. Nevertheless, most research efforts have been concerned with only within-state nonstationarity, e.g., variable state duration and regional symbol correlation. In this paper we explore the nonstationarity of Markov chains and propose a nonstationary HMM that is defined with a set of dynamic transition probability parameters A( τ) = { a ij ( τ)}, a function of time duration τ. The model, when compared to the traditional models, is defined as a generalization of the standard HMM and the state duration HMM, with the description being given for discrete observation distributions. Through a set of experiments, it has been shown that the proposed model is more capable of capturing the dynamic nature of signals with higher discrimination power in on-line character recognition.

State duration modelling in hidden Markov models

A new method is proposed for modelling state duration in hidden Markov model (HMM) speech recognition systems. State transition probabilities are expressed conditional on how long the current state has been occupied. The conventional fixed-state transition probabilities a ij are replaced by duration-dependent variables a ij ( d) that depend on the time d already spent in state i. In this way, state transition and state duration probabilities are combined to form duration-dependent transition probabilities. The transition probabilities are derived from the cumulative density function (CDF) of state duration. The training of HMM s with duration-dependent transitions are based on maximum likelihood segmentation of training data, using the Viterbi algorithm. At each training iteration, the current HMM parameters are used to segment every training example. All the segments associated with each state are then used to update state observation and transition parameters. In experiments with a data set of spoken English alphabet, durational modelling improves the recognition accuracy by 5.6%.