Phone Duration Research Articles

Digital Addiction in Children and Affecting Factors.

This study was conducted to identify the digital addiction levels of secondary school students in Northern Cyprus and the factors affecting them. The study was a descriptive, cross-sectional and methodological study. In this study, seven primary and secondary schools were selected randomly in Northern Cyprus and a total of 844 students were included in the study. The children scored 48.12 ± 17.46 points on the "Digital Addiction Scale for Children". Gender, economic status, age, reasons for using the internet, own cell phone, duration of cell phone and computer use, own computer, mother's education and place of residence significantly affected the children's digital addiction level (p < 0.05). Digital tools have entered many areas of our lives and while they have positive and helpful aspects, their negative aspects are coming to light day by day. Especially with the COVID-19 pandemic, digital tools have entered our lives more and children have encountered digital tools at an earlier age. It is thought that there is a need to warn about the negative and harmful effects of digital tools on children and to inform families more about this issue. It is recommended not to ignore the negative effects of digital tools and to implement practices to prevent addiction under parental supervision.

Correlation of mobile phone usage on grip strength, disabilities and posture in young adults

Background: The musculoskeletal issues are now common in excessive use of mobile phone for communication, gamming and socialization on internet. The excessive use of mobile phone may decrease the muscle strength and lead to poor posture ultimately functional impairment related to upper extremity. Objective: to determine correlation among duration of mobile phone usage, neck posture, disabilities and hand grip strength. Methods: A correlational cross sectional study was done at Riphah International University Lahore from March 2020 to February 2021. The target population was male and female young students of 18 to 24 years, used mobile phone more than 6 hours in a day. A total of n=400 subjectsarticipated in the study in which n=235 were females and n=165 were males. The information was gathered using the DASH Questionnaire to identify upper limb problems, the photogrammetry method to determine the cervical angle, and a dynamometer to determine the strength of each hand's grasp. The pearson product-moment correlation coefficient was done by using SPSS version 21. Result: The mean age of the study participant was 20.99±2.34 years. A total of n=165(41.25%) were male and remaining n=235 were female participated in the study. Increase use of mobile had negative significant small correlation with degree of cervical angle (p=0.04), right hand grip strength (p=0.01) and positive significant small correlation with DASH score (0.01). While no significant correlation between daily use of mobile phone and left hand grip strength Conclusion: The study concluded that as the duration of mobile phone usage increased, the forward head posture and disabilities of the upper limb also increased. But the grip strength of right hand decreased as the mobile phone duration is increased. Key words: Correlation, disabilities, female, grip strength, mobile phone, male, posture.

Phone duration modeling for speaker age estimation in children.

Automatic inference of paralinguistic information from speech, such as age, is an important area of research with many technological applications. Speaker age estimation can help with age-appropriate curation of information content and personalized interactive experiences. However, automatic speaker age estimation in children is challenging due to the paucity of speech data representing the developmental spectrum, and the large signal variability including within a given age group. Most prior approaches in child speaker age estimation adopt methods directly drawn from research on adult speech. In this paper, we propose a novel technique that exploits temporal variability present in children's speech for estimation of children's age. We focus on phone durations as biomarker of children's age. Phone duration distributions are derived by forced-aligning children's speech with transcripts. Regression models are trained to predict speaker age among children studying in kindergarten up to grade 10. Experiments on two children's speech datasets are used to demonstrate the robustness and portability of proposed features over multiple domains of varying signal conditions. Phonemes contributing most to estimation of children speaker age are analyzed and presented. Experimental results suggest phone durations contain important development-related information of children. The proposed features are also suited for application under low data scenarios.

Temporal and spectral characteristics of conversational versus read fricatives in American English.

The present study compares the production of fricatives in conversational versus read speech in American English. The goal is to examine which parameters contribute to the identification of fricatives across the two speech styles. The study surveys over 162 000 fricative tokens from the Buckeye Corpus [Pitt, Johnson, Hume, Kiesling, and Raymond (2005). Speech Commun. 45, 89-95] and the TIMIT Corpus [Zue and Seneff (1996). Recent Research towards Advanced Man-Machine Interface through Spoken Language (Elsevier, Amsterdam, the Netherlands), pp. 515-525]. A total of 18 different temporal and spectral measures are tested, including segment duration, preceding and following phone duration, spectral moments (at onset, midpoint, and/or offset), spectral peak frequency, etc. Results show that segment duration and midpoint spectral moments make the most prominent contribution to the categorization of fricatives for both speech styles. Spectral measures are more important for conversational speech, whereas duration plays a greater role for read speech. At the same time, the magnitude of the differences across speech styles is often low and many of the observed effects may be attributable to methodological differences across the corpora. Results may indicate that reduction of fricatives in conversational speech is more limited compared to the reduction of other types of speech sounds, such as plosives.

Association between electronic device usage and sperm quality parameters in healthy men screened as potential sperm donors

Cell phone use and radio-frequency electromagnetic radiation (RF-EMF) are rapidly increasing and may be associated with lower semen quality, yet results from epidemiological studies are inconclusive. Information on electronic devices use was collected through standard questionnaires from 1454 men aged 22–45 years old. Semen volume, sperm concentration, total sperm count, total motility, progressive motility, and normal morphology in repeated specimens were determined by trained clinical technicians. Percent changes [95% confidence intervals (CIs)] were estimated as (10β−1) × 100 for electronic devices use associated with repeated sperm quality parameters in the linear mixed-effect models. After adjusting for multiple confounders, we found significant inverse associations of total duration of electronic devices use with sperm progressive motility and total motility, duration of cell phone and computer use with sperm concentration, progressive motility, and total motility (all P < 0.05). No significant association was found between cell phone/computer use alone and sperm quality parameters. Moreover, per hour increase of time spent on cell phone talking was associated with decreased sperm concentration and total count by an average of −8.0% (95% CI: −15.2%, −0.2%) and −12.7% (95% CI: −21.3%, −3.1%), respectively. Besides, daily calling time was associated with lower sperm progressive motility and total motility among those who used headsets during a call (P for interaction <0.05). In conclusion, our study suggested that more time spent on electronic devices use had a modest reduction effect on semen quality. Daily calling time was significantly associated with lower sperm concentration and total count, and using headsets during a call appeared to aggravate the negative association between daily calling time and sperm motility. Additional studies are needed to confirm these findings.

Prosody-TTS: An End-to-End Speech Synthesis System with Prosody Control

End-to-end text-to-speech synthesis systems achieved immense success in recent times, with improved naturalness and intelligibility. However, the end-to-end models, which primarily depend on the attention-based alignment, do not offer an explicit provision to modify/incorporate the desired prosody while synthesizing the speech. Moreover, the state-of-the-art end-to-end systems use autoregressive models for synthesis, making the prediction sequential. Hence, the inference time and the computational complexity are quite high. This paper proposes Prosody-TTS, a data-efficient end-to-end speech synthesis model that combines the advantages of statistical parametric models and end-to-end neural network models. It also has a provision to modify or incorporate the desired prosody at the finer level by controlling the fundamental frequency (\(f_0\)) and the phone duration. Generating speech utterances with appropriate prosody and rhythm helps in improving the naturalness of the synthesized speech. We explicitly model the duration of the phoneme and the \(f_0\) to have a finer level control over them during the synthesis. The model is trained in an end-to-end fashion to directly generate the speech waveform from the input text, which in turn depends on the auxiliary subtasks of predicting the phoneme duration, \(f_0\), and Mel spectrogram. Experiments on the Telugu language data of the IndicTTS database show that the proposed Prosody-TTS model achieves state-of-the-art performance with a mean opinion score of 4.08, with a very low inference time using just 4 hours of training data.

Technological Devices and Their Effect on Preschool Children's Eating Habits in Communities of Mixed Socioeconomic Status in Istanbul; a Pilot Cross-Sectional Study.

The use of technological devices is increasing in all age groups, especially in preschool-aged children. However, there is a limiting number of studies investigating the relationship between the use of technological devices, eating behavior, and weight status in preschool children. The aim of this study was (1) to describe total usage of technological devices, (2) to evaluate level of exclusive use of such devices by children, (3) to investigate children’s eating behaviors and diet in relation to screen time and type. A cross-sectional study was conducted with 104 children aged 2–5 years in Küçükçekmece and Bakırköy, Istanbul. Data collection consisted of a validated parental questionnaire on demographics and the child’s use of technology and eating behavior, while associations in children were examined using logistic regression analysis. The analysis of the obtained data uncovered a strong association between children’s TV and tablet/smart phone use and the foods consumed by children when using these devices (p = 0.0001; p = 0.012). Also, there was a significant association between children’s eating habits and TV, and tablet/smart phone durations of use (p = 0.015; p = 0.025), but not with computer duration of use (p > 0.05). Obesity and associated health problems can arise as results of suboptimal eating behavior, such as the ones observed in our study, which are also intensified with an increased duration of use of technological devices. The attitude of families towards prudent use of technological equipment is of great importance in impacting present and future health.

Learning emotions latent representation with CVAE for text-driven expressive audiovisual speech synthesis

Great improvement has been made in the field of expressive audiovisual Text-to-Speech synthesis (EAVTTS) thanks to deep learning techniques. However, generating realistic speech is still an open issue and researchers in this area have been focusing lately on controlling the speech variability. In this paper, we use different neural architectures to synthesize emotional speech. We study the application of unsupervised learning techniques for emotional speech modeling as well as methods for restructuring emotions representation to make it continuous and more flexible. This manipulation of the emotional representation should allow us to generate new styles of speech by mixing emotions. We first present our expressive audiovisual corpus. We validate the emotional content of this corpus with three perceptual experiments using acoustic only, visual only and audiovisual stimuli. After that, we analyze the performance of a fully connected neural network in learning characteristics specific to different emotions for the phone duration aspect and the acoustic and visual modalities. We also study the contribution of a joint and separate training of the acoustic and visual modalities in the quality of the generated synthetic speech. In the second part of this paper, we use a conditional variational auto-encoder (CVAE) architecture to learn a latent representation of emotions. We applied this method in an unsupervised manner to generate features of expressive speech. We used a probabilistic metric to compute the overlapping degree between emotions latent clusters to choose the best parameters for the CVAE. By manipulating the latent vectors, we were able to generate nuances of a given emotion and to generate new emotions that do not exist in our database. For these new emotions, we obtain a coherent articulation. We conducted four perceptual experiments to evaluate our findings.

Behavior Characterization of Use of Mobile Phones which Potentially Cause Health Problems of Elementary School-Age Children in Rural and Urban Areas

Introduction: The development of communication technology meets a siginificant advancement, and mobile phones are part of it. Mobile phones are used not only by adults but also by children, including elementary school age children. Children in using mobile phones have different behavior based on their social, economic and cultural differences. Some behaviors of children in using mobile phones have a risk of health problems. Objective: The purpose of the study was to characterize the behavior of the use of mobile phones in primary school age children which could potentially cause health problems. Methods: This is a descriptive study using cross-sectional design. The study involved 60 children and their parents in urban and rural elementary schools. Data were collected by questionnaire (there were 13 questions) using the Google form application (close ended questionnaire) from population taken by the nonprobability sampling method. The data obtained were analyzed using descriptive analysis. Results: The results found that the possession of mobile phones, lighting, place and duration of use mobile phones were behaviors that descriptively showed that there were differences between children from rural and urban elementary schools. Behavior of time using mobile phones, body position, alignment and distance of the mobile phone to the head or eye, the purpose, tool and the place where to use the cellphone, both groups have the same percentage. Conclussion: there are differences and similarities in behavior in using mobile phones between children from rural and urban elementary schools.

Duration modelling and evaluation for Arabic statistical parametric speech synthesis

Sound duration is responsible for rhythm and speech rate. Furthermore, in some languages phoneme length is an important phonetic and prosodic factor. For example, in Arabic, gemination and vowel quantity are two important characteristics of the language. Therefore, accurate duration modelling is crucial for Arabic TTS systems. This paper is interested in improving the modelling of phone duration for Arabic statistical parametric speech synthesis using DNN-based models. In fact, since a few years, DNN have been frequently used for parametric speech synthesis, instead of HMM. Therefore, several variants of DNN-based duration models for Arabic are investigated. The novelty consists in training a specific DNN model for each class of sounds, i.e. short vowels, long vowels, simple consonants and geminated consonants. The main idea behind this choice is the improvement that we already achieved in the quality of Arabic parametric speech synthesis by the introduction of two specific features of Arabic, i.e. gemination and vowel quantity into the standard HTS feature set. Both objective and subjective evaluations show that using a specific model for each class of sounds leads to a more accurate modelling of the phone duration in Arabic parametric speech synthesis, outperforming the state-of-the-art duration modelling systems.

Significance of spectral cues in automatic speech segmentation for Indian language speech synthesizers

Building speech synthesis systems for Indian languages is challenging owing to the fact that digital resources for these languages are hardly available. Vocabulary independent speech synthesis requires that a given text is split at the level of the smallest sound unit, namely, phone. The waveforms or models of phones are concatenated to produce speech. The waveforms corresponding to that of the phones are obtained manual (listening and marking) when digital resources are scarce. But the manual labeling of speech data (also known as speech segmentation) can lead to inconsistencies as the duration of phones can be as short as 10ms.The most common approach to automatic segmentation of speech is to perform forced alignment using monophone hidden Markov models (HMMs) that have been obtained using embedded re-estimation after flat start initialization. These results are then used in neural network frameworks to build better acoustic models for speech synthesis/recognition. Segmentation using this approach requires large amounts of data and does not work very well for low resource languages. To address the issue of paucity of data, signal processing cues like short-term energy (STE) and sub-band spectral flux (SBSF) are used in tandem with HMM based forced alignment for automatic speech segmentation.STE and SBSF are computed on the speech waveforms. STE yields syllable boundaries, while SBSF provides locations of significant change in spectral flux that are indicative of fricatives, affricates, and nasals. STE and SBSF cannot be used directly to segment an utterance. Minimum phase group delay based smoothing is performed to preserve these landmarks, while at the same time reducing the local fluctuations. The boundaries obtained with HMMs are corrected at the syllable level, wherever it is known that the syllable boundaries are correct. Embedded re-estimation of monophone HMM models is again performed using the corrected alignment. Thus, using signal processing cues and HMM re-estimation in tandem, robust monophone HMM models are built. These models are then used in Gaussian mixture model (GMM), deep neural network (DNN) and convolutional neural network (CNN) frameworks to obtain state-level frame posteriors. The boundaries are again iteratively corrected and re-estimated.Text-to-speech (TTS) systems are built for different Indian languages using phone alignments obtained with and without the use of signal processing based boundary corrections. Unit selection based and statistical parametric based TTS systems are built. The result of the listening tests showed a significant improvement in the quality of synthesis with the use of signal processing based boundary correction.

A study on default prediction of Chinese online lending: based on the analysis of mobile phone usage data

ABSTRACT Information asymmetry between online financial lenders and borrowers may lead to a high risk of overdue repayment. To identify the influencing factors of the default rate in Chinese online lending, the presented study was conducted using a dataset constructed by 5108 borrowers in an online lending platform between July 1 and September 30 in the year of 2019. This research adopted a logistic regression approach to investigate the influencing factors of borrowers’ defaults based on loan application time and borrowers’ mobile phone usage. The results show that the default rate is relatively low when the loan application is made during the daytime. Meanwhile, the study indicates that the default rate is negatively correlated with the most of the investigated parameters, which include the number of loan applications, the number of contacts, the duration of the mobile phone using the internet, and the number of one person’s multiple phone numbers. Based on observations of the presented research, it could be found that mobile phone usage data possesses a significant impact on the default prediction, which is capable of providing constructive guidance to effectively reduce default risk for the borrowers and the online lending platform.

Word class information in perception of prosodic prominence by Korean learners of English

This study aims to investigate how prosodic prominence is perceived in relation to word class information (or parts-of-speech) by Korean learners of English compared with native English speakers in public speech. Two groups, Korean learners of English and native English speakers, were asked to judge words perceived as prominent simultaneously while listening to a speech. Parts-of-speech and three acoustic cues (i.e., max F0, mean phone duration, and mean intensity) were analyzed for each word in the speech. The results showed that content words tended to be higher in pitch and longer in duration than function words. Both groups of listeners rated prominence on content words more frequently than on function words. This tendency, however, was significantly greater for Korean learners of English than for native English speakers. Among the parts-of-speech of the content words, Korean learners of English were more likely than native English speakers to judge nouns and verbs as prominent. This study presents evidence that Korean learners of English consider most, if not all, content words as landing locations of prosodic prominence, in alignment with the previous study on the production of prominence.

Objective smartphone data as a potential diagnostic marker of bipolar disorder

Currently, the diagnosis in bipolar disorder relies on patient information and careful clinical evaluations and judgements with a lack of objective tests. Core clinical features of bipolar disorder include changes in behaviour. We aimed to investigate objective smartphone data reflecting behavioural activities to classify patients with bipolar disorder compared with healthy individuals. Objective smartphone data were automatically collected from 29 patients with bipolar disorder and 37 healthy individuals. Repeated measurements of objective smartphone data were performed during different affective states in patients with bipolar disorder over 12 weeks and compared with healthy individuals. Overall, the sensitivity of objective smartphone data in patients with bipolar disorder versus healthy individuals was 0.92, specificity 0.39, positive predictive value 0.88 and negative predictive value 0.52. In euthymic patients versus healthy individuals, the sensitivity was 0.90, specificity 0.56, positive predictive value 0.85 and negative predictive value 0.67. In mixed models, automatically generated objective smartphone data (the number of text messages/day, the duration of phone calls/day) were increased in patients with bipolar disorder (during euthymia, depressive and manic or mixed states, and overall) compared with healthy individuals. The amount of time the smartphone screen was 'on' per day was decreased in patients with bipolar disorder (during euthymia, depressive state and overall) compared with healthy individuals. Objective smartphone data may represent a potential diagnostic behavioural marker in bipolar disorder and may be a candidate supplementary method to the diagnostic process in the future. Further studies including larger samples, first-degree relatives and patients with other psychiatric disorders are needed.

GPR-based Thai speech synthesis using multi-level duration prediction

This paper proposes a multi-level Gaussian process regression (GPR)-based method for duration prediction by incorporating phone- and syllable-level duration models. In this method, we first train the syllable model and predict syllable durations for a given input of context labels. Then, we use the predicted syllable duration as an additional context for the phone-level model to predict phone durations. To apply multi-level duration prediction to the GPR-based speech synthesis framework, we designed phone- and syllable- level context sets for Thai that include linguistic information and the relative positions of speech units. We also examined the multi-level deep neural network (DNN)-based duration-prediction method by using the same approach as for the proposed multi-level GPR-based one. We conducted objective and subjective evaluations using two-hour training data to compare the proposed method with single-level ones. The results indicate that the proposed multi-level duration-prediction method outperformed single-level ones in DNN-, and GPR-based frameworks. They also indicate that the proposed multi-level GPR-based method can provide better performance than the multi-level HMM-based duration-prediction method.

Automatic Speech Segmentation Using Hybrid Wavelet Features and HMM

In this research, a novel feature set is used to automatically segment speech signal. Automatic segmentation is veryuseful especially for large database. A hybrid features model is created from wavelet packet analysis and mel-scale is used to train Hidden Markov Model (HMM) for phone boundary detection. HMM is implemented using the Hidden Markov Model Toolkit (HTK).The database (Ked-TIMIT) is used for result verifications and Mel Frequency Cepstral Coefficients (MFCC) is used as reference for evaluating the results of the proposed Hybrid model. The results are categorized for vowels, consonants and short phones. Phone duration and start location are used as metrics to evaluate the system success rate. Success rate of 74% is achieved for consonant detection, 72% for vowel detection and 58% for short phone detection. Using the simple metric that relies only on boundary locations but ignoring duration, the achieved results are 92.5% for consonant detection, 90% for vowel detection and 77.5% for short phoneme detection. In addition to boundary detection the proposed hybrid model is utilized to compare newly developed features called Mel scale Best Tree Encoding (Mel-BTE ) to the mostly used popular features MFCC along with all experiments using the same database. The relative results for Mel-BTE with respect to MFCC are 94.77% for consonant detection, 87.5% for vowel detection and 93.33% for short phoneme detection.

Twenty-five years of advocacy for patients with gastroparesis: support group therapy and patient reported outcome tool development.

BackgroundGastroparesis (Gp) is a poorly understood chronic gastrointestinal medical condition for which patient reported outcomes (PRO) are lacking. Previously developed symptoms scoring has been used for several decades. Using symptoms scores as a basis for documentation, 12 years of support/focus group patient feedback from the nearly 1000 attendees were integrated with medical care and recommendations for treatment were developed. Early attenders of the support group were compared with non-attendees for illness acuity, disability, and duration and number of office phone calls.MethodsPatients cared for in an academic medical practice were assessed for patient-derived PRO symptoms, coupled with standardized Health Related Quality of Life (HRQOL) measures. Based on factors identified by the patients via support/focus groups, a diagnostic and prognostic tool was developed.ResultsThe new tool utilized PRO symptoms and included provider assessments of medical illnesses as well as resource utilization. This ‘post PRO’ tool has been applied in a variety of settings for patients with the symptoms of Gp over the last two decades. The ‘pre-PRO’ factors from the support/focus groups were compared to the PRO measures as well as the ‘post-PRO’ scale to assess their usefulness. Using methods that combine chart data, including electronic medical records (EMR), with PRO symptoms may have design implications for PRO assessment. The resultant scales, as part of a new tool, can allow for sharing of PRO derived scores in a chronic gastrointestinal (GI), illness with different practitioners.ConclusionsThese newly-derived scales offer a potentially useful tool for clinical decision-making, tailoring treatment to patient subgroups and engaging both patients and their families and caregivers in more active partnerships with providers to improve health outcomes.Electronic supplementary materialThe online version of this article (doi:10.1186/s12876-016-0523-3) contains supplementary material, which is available to authorized users.

Musculoskeletal impact of the use of various types of electronic devices on university students in Hong Kong: An evaluation by means of self-reported questionnaire

IntroductionDespite the increasingly widespread popularity of electronic devices, there are limited comprehensive studies on the effects of usage and exposure to multiple electronic devices over extended periods of time. Therefore, this study explored the cumulative musculoskeletal implications of exposure to various electronic devices among university students. MethodsA self-reported questionnaire was administered in the university in Hong Kong and students provided information about the frequency and duration of electronic devices use, including computers, mobile phones and game consoles, and reported on any musculoskeletal pain or discomfort that may relate to electronic devices usage in the immediate 12 months prior to the survey date. ResultsA total of 503 university students (59% males and 41% females) aged 18–25 years completed the questionnaire. The results showed that 251 (49.9%) respondents reported upper limb musculoskeletal symptoms, particularly in the neck and shoulder regions. Among these, 155 (61.8%) indicated that their discomfort was related to electronic device usage. Statistically significant differences in exposure to electronic devices and musculoskeletal outcomes between genders were found (p < 0.05). ConclusionThe use of electronic devices and habitual postures were associated with musculoskeletal problems among university students in Hong Kong. This phenomenon highlights the urgent need for ergonomics education and recommendations to increase students' awareness of musculoskeletal wellbeing.

Detection of Sentence Boundaries in Polish Based on Acoustic Cues

Abstract In this article the authors investigated and presented the experiments on the sentence boundaries annotation from Polish speech using acoustic cues as a source of information. The main result of the investigation is an algorithm for detection of the syntactic boundaries appearing in the places of punctuation marks. In the first stage, the algorithm detects pauses and divides a speech signal into segments. In the second stage, it verifies the configuration of acoustic features and puts hypotheses of the positions of punctuation marks. Classification is performed with parameters describing phone duration and energy, speaking rate, fundamental frequency contours and frequency bands. The best results were achieved for Naive Bayes classifier. The efficiency of the algorithm is 52% precision and 98% recall. Another significant outcome of the research is statistical models of acoustic cues correlated with punctuation in spoken Polish.

A fast hierarchical search algorithm for discriminative keyword spotting

A keyword spotter can be considered as a binary classifier which classifies a set of uttered sentences into two groups on the basis of whether they contain target keywords or not. For this classification task, the keyword spotter needs to identify the target keywords locations based on a fast and accurate search algorithm. In our previous works, we exploited a modified Viterbi (M-Viterbi) search algorithm which has two known drawbacks. First, to locate the target keywords, it runs an exhaustive search through all possible segments of input speech. Second, while computing the start and end time-frames of each new phone, it makes the keyword spotter to trace-back and re-evaluate the timing alignments of all previous one(s), despite the fact that very limited amount of data -if any- would get updated as a result. These two pitfalls cause a dramatically enlarged search space as well as a significant increase in computational complexity. In this paper, we propose a Hierarchical Search (H-Search) algorithm which allows the system to ignore some segments of input speech at each level of hierarchy, according to their lower likelihood of containing the target keywords. In addition, unlike the M-Viterbi algorithm, the H-Search algorithm does not demand repeated evaluations when computing the current phone alignment which, in turn, results in a narrowed-down search space (O(TP) versus O(TPLmax) – where T is number of frames, P is number of keyword phones and Lmax is the maximum phone duration) as well as a decreased computational complexity (O(TPLmax) versus O(TPLmax3)) compared to those of the M-Viterbi algorithm. We applied the H-Search algorithm to the classification part of an Evolutionary Discriminative Keyword Spotting (EDKWS) system introduced in our previous works. The experimental results indicate that the H-Search algorithm is executed 100 times faster than the M-Viterbi algorithm while the performance of the EDKWS system degrades no more than two percent compared to that of the M-Viterbi algorithm.