Hidden Markov Model-Based Research Articles

A TDOA sequence estimation method of underwater sound source based on hidden Markov model

To address the time difference of arrival (TDOA) estimation problem in the passive positioning system with wideband underwater motion sound sources and distributed hydrophones, a hidden Markov model-based (HMM) TDOA sequence estimation method is proposed in this paper. The method estimates the TDOA with multi-frame output of cross-correlated signals received on hydrophones. The transfer equation of the TDOA is established as a first-order hidden Markov process by analyzing the motion characteristics of the moving sound source and delays obtained from different hydrophones. Dynamic assignment of the HMM parameters is proposed to address the inconsistent change rate of the TDOA. We then achieve an HMM expression of the TDOA sequence by fitting the transfer equation and dynamic assignment of parameters into the HMM. Then, the Viterbi algorithm (VA) is applied to distinguish the optimal sequence of the TDOA among ambiguous estimations. To deal with the problem of data loss or unreliable issues caused by interferences, a data prediction algorithm which could produce possible time delays is added to VA to avoid the impact of outliers on the estimation results. By utilizing multi-frame processing, the proposed method reduces the signal-to-noise ratio (SNR) requirement of single frames since it does not require accurate estimations of TDOA for each frame. Moreover, the method adapts to a lower SNR, which has significant advantages in terms of whole sequence estimation compared with common methods. The results from the simulations and lake experiments validated the proposed TDOA sequence estimation method.

Finding RNA-Protein Interaction Sites Using HMMs.

RNA-binding proteins play important roles in the various stages of RNA maturation through binding to its target RNAs. Cross-linking immunoprecipitation coupled with high-throughput sequencing (CLIP-Seq) has made it possible to identify the targeting sites of RNA-binding proteins in various cell culture systems and tissue types on a genome-wide scale. Several Hidden Markov model-based (HMM) approaches have been suggested to identify protein-RNA binding sites from CLIP-Seq datasets. In this chapter, we describe how HMM can be applied to analyze CLIP-Seq datasets, including the bioinformatics preprocessing steps to extract count information from the sequencing data before HMM and the downstream analysis steps following peak-calling.

Punjabi Speech Synthesis System using HTK

This paper describes an Hidden Markov Model-based Punjabi text-to-speech synthesis system (HTS), in which speech waveform is generated from Hidden Markov Models themselves, and applies it to Punjabi speech synthesis using the general speech synthesis architecture of HTK (HMM Tool Kit). This Hidden Markov Model based TTS can be used in mobile phones for stored phone directory or messages. Text messages and caller’s identity in English language are mapped to tokens in Punjabi language which are further concatenated to form speech with certain rules and procedures. To build the synthesizer we recorded the speech database and phonetically segmented it, thus first extracting context-independent monophones and then context-dependent triphones. For e.g. for word bharat monophones are a, bh, t etc. & triphones are bh-a+r. These speech utterances and their phone level transcriptions (monophones and triphones) are the inputs to the speech synthesis system. System outputs the sequence of phonemes after resolving various ambiguities regarding selection of phonemes using word network files e.g. for the word Tapas the output phoneme sequence is �,�,� instead of phoneme sequence

USING NONLINEAR MODELING OF RECONSTRUCTED PHASE SPACE AND FREQUENCY DOMAIN ANALYSIS TO IMPROVE AUTOMATIC SPEECH RECOGNITION PERFORMANCE

This paper introduces a combinational feature extraction approach to improve speech recognition systems. The main idea is to simultaneously benefit from some features obtained from nonlinear modeling applied to speech reconstructed phase space (RPS) and typical Mel frequency Cepstral coefficients (MFCCs) which have a proved role in speech recognition field. With an appropriate dimension, the reconstructed phase space of speech signal is assured to be topologically equivalent to the dynamics of the speech production system, and could therefore include information that may be absent in linear analysis approaches. In the first part of this paper the application of Lyapunov Exponents (LE) and Fractal Dimension as two usual chaotic features in speech recognition are tested and then a short discussion is made on the weakness of these features in speech recognition. In the following, a statistical modeling approach based on Gaussian mixture models (GMMs) is applied to speech RPS. A final pruned feature set is obtained by applying an efficient feature selection approach to the combination of the parameters of the GMM model and MFCC-based features. A hidden Markov model-based (HMM) speech recognition system and TIMIT speech database are used to evaluate the performance of the proposed feature set by conducting isolated and continuous speech recognition experiments. In final Continuous Speech Recognition (CSR) Experiments, using tri-phone models, 3.7% absolute phoneme recognition accuracy improvement against using MFCC features alone were obtained.

Design of Tree Structure in Context Clustering Process of Hidden Markov Model-Based Thai Speech Synthesis

Problem statement: In HMM-based Thai speech synthesis, the tone degradation due to the imbalance of training data of all tones. Some distortion of syllable duration is obviously noticeable when the system is trained with a small amount of data. These problems cause the decrement in naturalness and intelligibility of the synthesized speech. Approach: This study proposes an approach to improve the correctness of tone of the synthesized speech which is generated by an HMM-based Thai speech synthesis system. In the tree-based context clustering process, tone groups and tone types are used to design four different structures of decision tree including a single binary tree structure, a simple tone-separated tree structure, a constancy-based-tone-separated tree structure and a trend-based-tone-separated tree structure. Results: A subjective evaluation of tone correctness is conducted by using tone perception of eight Thai listeners. The simple tone-separated tree structure gives the highest level of tone correctness, while the single binary tree structure gives the lowest level of tone correctness. The additional contextual tone information which is applied to all structures of the decision tree achieves a significant improvement of tone correctness. Finally, the evaluation of syllable duration distortion among the four structures shows that the constancy-based-tone-separated and the trend-based-tone-separated tree structures can alleviate the distortions that appear when using the simple tone-separated tree structure. Conclusion: The appropriate structure of tree in context clustering process with the additional contextual tone information can improve the correctness of tones, while the constancy-based-tone-separated and the trend-based-tone-separated tree structures can alleviate the syllable duration distortions.

A Control of Fundamental Frequency Contour for Hidden Markov Model-Based Thai Speech Synthesis

Problem statement: In the conventional HMM-based speech synthesis system for Thai, there is no control of fundamental frequency control in the synthesis stage. The tone correctness of the synthesized speech is unacceptable due to the imbalance of training data of all tones. Approach: This study proposes a mathematical model to control the F0 contour of the synthesized speech. This control is proposed to correct only some distorted segments of the F0 contour which occur within some syllables due to lacking of training data for some tones. Results: An experimental result compares F0 contours between those of synthesized speech with and without tone-type questions; furthermore the size of Thai speech corpus is varied to investigate the synthesized speech quality. A mathematical model is applied to control the F0 contour. By using the proposed control, the correction of the F0 contour is obviously shown in the experimental results. Conclusion: The control of F0 contour has been proposed. It can noticeably improve the tone correctness of the synthesized speech.

Investigating the Need for Modelling Temporal Dependencies in a Brain-Computer Interface with Real-Time Feedback Based on near Infrared Spectra

Near infrared (NIR) spectroscopy is an emerging non-invasive brain-computer interface (BCI) modality that measures changes in haemoglobin concentrations in neurocortical tissue. Previous NIR spectroscopy studies have not employed real-time feedback with online classification, a combination which would allow users to alter their mental strategy on the fly. In particular, it is unclear whether or not the temporal dependencies of haemodynamic changes ought to be considered in online classification. To answer this quest ion, this study contrasted online classification of prefrontal haemodynamics using NIR spectra processed using two approaches: an artificial neural network (ANN) that considered instantaneous samples of oxy- and deoxy-haemoglobin concentrations (i.e. ignored temporal dependencies) and a hidden Markov model-based (HMM) classifier which modelled a temporal sequence of concentrations (i.e. embodied temporal dependencies). Both classifiers were implemented for online operation with immediate visual feedback via a monitor showing a vertical bar the height of which was contingent on the classifier's output. Ten subjects participated in two study sessions each, one with each type of classifier. Participants were cued to raise and lower the bar in alternating 20s intervals using mental fast singing and focused breathing, respectively. Only the ANN classifier facilitated online classification rates greater than chance ( P = 0.0289). The influence of physiological noise on online classification of prefrontal haemodynamics was deemed to be minimal via offline analysis of concurrently measured respiration and blood pulse. Nine of the ten participants reported using the feedback to alter their activation strategy. Mental fatigue, task repetitiveness and the lack of ambient lighting were identified as factors compromising performance in half the participants. The inferior performance of the HMM classifiers suggests that modelling of the temporal dynamics of haemoglobin concentration changes may not be necessary in an online NIR-BCI. Further study of online NIR-BCIs with instantaneous feedback is warranted.

Improvements of Hungarian hidden Markov model-based text-to-speech synthesis

Statistical parametric, especially Hidden Markov Model-based, text-to-speech (TTS) synthesis has received much attention recently. The quality of HMM-based speech synthesis approaches that of the s...

Multi-Modal Dialog Scene Detection Using Hidden Markov Models for Content-Based Multimedia Indexing

A class of audio-visual data (fiction entertainment: movies, TV series) is segmented into scenes, which contain dialogs, using a novel hidden Markov model-based (HMM) method. Each shot is classified using both audio track (via classification of speech, silence and music) and visual content (face and location information). The result of this shot-based classification is an audio-visual token to be used by the HMM state diagram to achieve scene analysis. After simulations with circular and left-to-right HMM topologies, it is observed that both are performing very good with multi-modal inputs. Moreover, for circular topology, the comparisons between different training and observation sets show that audio and face information together gives the most consistent results among different observation sets.