Speech Software Research Articles

Research on the interactive design of intelligent assisted speech software

Nowadays, people need to make all kinds of speeches and presentations, both at school and at work. With the continuous development of science and technology, there is a lot of software on the market to assist people in making speeches. The aim of this article is to introduce the conception of a new type of presentation aid software and to analyse the development process of such software. Users from different backgrounds have evaluated the existing speech assistance software on the market, and this evaluation information will be based on the user reviews on the official website of the software download. Through the requirement analysis, the main problems and demands faced by the users in the presentation process will be identified. The software will be analysed and researched in terms of its design purpose, interface design, core functions, user experience and other aspects. The research conducted in this thesis provides users with new presentation assistance software that enables them to make more confident and smooth presentations. At the same time, this research provides useful references and discussions for the design and development of intelligent aids.

Effect of different personal protective equipment on sound discrimination in children using unilateral cochlear implants during the COVID-19 pandemic

ObjectivesThe COVID-19 pandemic obliged people to wear personal protective equipment (PPEs), which can harm verbal communication and speech intelligibility. The first aim was to study the impact of wearing PPEs on the voice and speech parameters of phoniatricians during therapy sessions. The second aim was to study the effect of phoniatricians wearing these PPEs on auditory discrimination of the Ling’s six sounds in children using unilateral cochlear implants.MethodsThe study was a case–control one, done in the phoniatrics outpatient clinics at Beni-Suef University and Cairo University hospitals. Four phoniatricians participated in this study, and the Dr. Speech software analyzed their speech and voice parameters during utterance of the Ling’s six sounds. Each phoniatrician uttered each Ling sound individually four times to assess fundamental frequency and intensity: first time without wearing any mask, second time while wearing a surgical mask, third time while wearing a face shield, and fourth time while wearing an N95 mask. The study also included forty patients using unilateral cochlear implants (group A) and forty children with normal peripheral hearing (group B). The phoniatricians again uttered the Ling’s six sounds to assess auditory discrimination in both groups. This subjective auditory discrimination was also tested in both groups four times: first time without wearing any mask, second time while wearing a surgical mask, third time while wearing a face shield, and fourth time while wearing an N95 mask.Results and conclusionThe intensity of Ling’s six sounds was significantly lowest in the face shield. Regardless of the PPE type, patients with unilateral cochlear implants showed less consonant discrimination of (mm) sound. Surgical masks and N95 provided the best acoustic performance, while face shields had the worst.

Digital assessment of speech in Huntington disease.

Speech changes are an early symptom of Huntington disease (HD) and may occur prior to other motor and cognitive symptoms. Assessment of HD commonly uses clinician-rated outcome measures, which can be limited by observer variability and episodic administration. Speech symptoms are well suited for evaluation by digital measures which can enable sensitive, frequent, passive, and remote administration. We collected audio recordings using an external microphone of 36 (18 HD, 7 prodromal HD, and 11 control) participants completing passage reading, counting forward, and counting backwards speech tasks. Motor and cognitive assessments were also administered. Features including pausing, pitch, and accuracy were automatically extracted from recordings using the BioDigit Speech software and compared between the three groups. Speech features were also analyzed by the Unified Huntington Disease Rating Scale (UHDRS) dysarthria score. Random forest machine learning models were implemented to predict clinical status and clinical scores from speech features. Significant differences in pausing, intelligibility, and accuracy features were observed between HD, prodromal HD, and control groups for the passage reading task (e.g., p < 0.001 with Cohen'd = -2 between HD and control groups for pause ratio). A few parameters were significantly different between the HD and control groups for the counting forward and backwards speech tasks. A random forest classifier predicted clinical status from speech tasks with a balanced accuracy of 73% and an AUC of 0.92. Random forest regressors predicted clinical outcomes from speech features with mean absolute error ranging from 2.43-9.64 for UHDRS total functional capacity, motor and dysarthria scores, and explained variance ranging from 14 to 65%. Montreal Cognitive Assessment scores were predicted with mean absolute error of 2.3 and explained variance of 30%. Speech data have the potential to be a valuable digital measure of HD progression, and can also enable remote, frequent disease assessment in prodromal HD and HD. Clinical status and disease severity were predicted from extracted speech features using random forest machine learning models. Speech measurements could be leveraged as sensitive marker of clinical onset and disease progression in future clinical trials.

RETRACTED ARTICLE: Application of speech software based on mobile network technology in oral English teaching and classroom feedback

RETRACTED ARTICLE: Application of speech software based on mobile network technology in oral English teaching and classroom feedback

Efficacy of straw phonation exercises with breathing exercises and indirect approaches for dysphonic adults with benign vocal fold lesions

Background: The voice is essential to a people’s daily life, especially in occupational voice users who are at risk for benign vocal fold lesions. It is important to use the proper vocal therapy techniques on a dysphonic patient who has benign vocal fold lesions in order to reduce behaviors that will aggravate the voice disorder and enhance behaviors that help improve voice quality. Objectives: The purpose of this study was to evaluate the efficacy of straw phonation exercises with breathing exercises and indirect approaches in dysphonic adults with benign vocal fold lesions, including vocal nodules; vocal polyps, and vocal cysts. Materials and methods: This study was a pilot study. Twelve participants who had benign vocal fold lesions received vocal hygiene guidance, abdominal breathing exercises, muscle relaxation, and straw phonation voice therapy. All participants received 8 weekly therapy sessions: 30 minutes per session. The vocal assessment data was collected before the first voice therapy session, and immediately after the eighth session, by subjective vocal assessment, and objective vocal assessment with Dr. Speech software version 5. Results: The results after therapy showed significant improvements against the GIRBAS scales in terms of the subjective vocal assessment, in the values of SD F0, jitter, NNE, and MPT of the objective vocal assessment. Conclusion: This result indicates straw phonation with breathing exercises and indirect approaches as being a worthwhile alternative method for voice therapy in dysphonic patients with benign vocal fold lesions.

Efficacy of straw phonation exercises with breathing exercises and indirect approaches for dysphonic adults with benign vocal fold lesions

Background: The voice is essential to a people’s daily life, especially in occupational voice users who are at risk for benign vocal fold lesions. It is important to use the proper vocal therapy techniques on a dysphonic patient who has benign vocal fold lesions in order to reduce behaviors that will aggravate the voice disorder and enhance behaviors that help improve voice quality. Objectives: The purpose of this study was to evaluate the efficacy of straw phonation exercises with breathing exercises and indirect approaches in dysphonic adults with benign vocal fold lesions, including vocal nodules; vocal polyps, and vocal cysts. Materials and methods: This study was a pilot study. Twelve participants who had benign vocal fold lesions received vocal hygiene guidance, abdominal breathing exercises, muscle relaxation, and straw phonation voice therapy. All participants received 8 weekly therapy sessions: 30 minutes per session. The vocal assessment data was collected before the first voice therapy session, and immediately after the eighth session, by subjective vocal assessment, and objective vocal assessment with Dr. Speech software version 5. Results: The results after therapy showed significant improvements against the GIRBAS scales in terms of the subjective vocal assessment, in the values of SD F0, jitter, NNE, and MPT of the objective vocal assessment. Conclusion: This result indicates straw phonation with breathing exercises and indirect approaches as being a worthwhile alternative method for voice therapy in dysphonic patients with benign vocal fold lesions.

Combined Influences of Stress and Fibromyalgia on Voice: A Single-case Report

Abstract Fibromyalgia may occur due to muscle tension while speaking or singing inaccurately. Symptoms of fibromyalgia are pain, fatigue, alteration in sleep, cognitive dysfunction, anxiety, depression, intestinal disorders, voice, and mood. Women are more affected than men. Voice was evaluated using the GRBAS scale and Dr. Speech software. Perceptually, voice was minimal dysphonia, and acoustically, voice parameters were within normal limits except harmonic–to-noise ratio.

Use of ASR-Equipped Software in the Teaching of Suprasegmental Features of Pronunciation

Technology has paved the way for new modalities in language learning, teaching, and assessment. However, there is still a great deal of work to be done to develop such tools for oral communication, specifically tools that address suprasegmental features in pronunciation instruction. Therefore, this critical literature review examines how researchers have tried to create computer-assisted pronunciation training tools using automatic speech recognition (ASR) systems to aid language learners in the perception and production of suprasegmental features. We used 30 texts from 1990 to 2020 to explore how technologies have been and are currently being used to help learners develop their proficiency with suprasegmental features. Based on our thematic analysis, a persistent gap still exists between ASR-equipped software available to participants in research studies and what is available to university and classroom teachers and students. Additionally, there seems to be more development in the production of speech software for language assessment. In contrast, the translation of these tools into instructional tools for individualized learning seems to be almost non-existent. Moving forward, we recommend that more commercialized pronunciation systems utilizing ASR should be made publicly available using the technologies that are currently developed or are in development for the purposes of oral proficiency judgments.

Effect of Text-to-speech Software on Academic Achievement of Students with Dyslexia

Dyslexia is a neurobiological disorder that creates serious difficulties in learning process. Being a special learning disorder, it demands special learning environment with a blend of right approach, method and technology. Text to speech software comes under the head of assistive technology that helps dyslexic children understand and assimilate structure sound and meaning of the words. Present study is an experimental study in which 20 students of 6-12 years of age range were selected and randomly distributed in experimental and control group. Experimental group was taught with text to speech software for four months while control group received no treatment and was taught by conventional method of teaching. In the beginning of the study a pretest was conducted in order to know the prevalent differences among the groups. After four months of intervention post test was conducted. Results revealed that students in experimental group performed significantly better than the control group. Text to speech software contributed to remarkable gains in the achievement of students with dyslexia.

Self-access learning of English intonation with speech software: examining learners’ perceptions with a focus on their concerns and negative comments

Abstract Language laboratories exist in many language centres across the globe. Situated in the popularity of self-access and computer-assisted language learning in the present era, the study investigated tertiary-level English as a foreign language (EFL) learners’ general and, particularly, negative views of speech analysis software. Two hundred and eighty intermediate-level (CEFR B1 and B2 levels) EFL participants completed trial sessions with some free speech software in which they listened to and recorded utterances to practise English intonation at a language laboratory in Hong Kong. Each participant was observed during the session, completed a questionnaire, and attended a brief post-questionnaire interview after the session. Both quantitative and qualitative data were collected. The results showed that learning with this kind of software was perceived generally positively in relation to language enhancement and self-access learning. However, from the qualitative data collected about their negative views and concerns, three themes emerged: absence of a teacher, an interaction-less environment, and the little value of graphic outputs. This article concludes with a discussion of these findings and implications for language educators and researchers in self-access and computer-assisted language learning, which are in vogue globally nowadays. Suggestions for addressing learners’ negative views and comments, which have not received much attention among stakeholders, are also provided.

Characterizing speech heterogeneity in schizophrenia-spectrum disorders.

Schizophrenia-spectrum disorders (SSD) are highly heterogeneous in risk factors, symptom characteristics, and disease course outcome. Although speech anomalies have long been recognized as a core symptom of SSD, speech markers are an unexplored source of symptom heterogeneity that may be informative in recognizing relevant subtypes. This study investigated speech heterogeneity and its relation to clinical characteristics in a large sample of patients with SSD and healthy controls. Speech samples were obtained from 142 patients with SSD and 147 healthy controls by means of open-ended interviews. Speech was analyzed using standardized open-source acoustic speech software. Hierarchical clustering was conducted using acoustic speech markers. Symptom severity was rated with the Positive and Negative Syndrome Scale, and cognition was assessed with the Brief Assessment of Cognition for Schizophrenia. Three speech clusters could be distinguished in the patient group that differed regarding speech properties, independent of medication use. One cluster was characterized by mild speech disturbances, while two severely impaired clusters were recognized (fragmented speakers and prolonged pausers). Both clusters with severely impaired speech had more severe cognitive dysfunction than the mildly impaired speakers. Prolonged pausers specifically had difficulties with memory-related tasks. Prolonged pausing, as opposed to fragmented speaking, related to chronic active psychosis and refractory psychotic symptoms. Based on speech clustering, subtypes of patients emerged with distinct disease trajectories, symptomatology, and cognitive functioning. The identification of clinically relevant subgroups within SSD may help to characterize distinct profiles and benefit the tailoring of early intervention and improvement of long-term functional outcome. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Mucosal Bridge Reconstruction: A Novel Approach for the Vocal Fold Mucosal Bridge.

Mucosal Bridges (MBs) are defined as benign connective tissue abnormalities of unclear etiology that extend over the free surface of the vocal fold, are attached to the front and back of the vocal fold but are not attached to its free surface, and are histologically covered by stratified squamous epithelium. In order to overcome these drawbacks, we aimed to retrospectively evaluate and present the preoperative and postoperative results of patients with MB, who were applied the method we call "Mucosal Bridge Reconstruction" (MBR), which we apply as suturing rather than resection of the MB. Between January 2016 and February 2020, 5 patients who applied to the voice clinic due to dysphonia and were diagnosed with MB via laryngostroboscopic examination and direct laryngoscopy under general anesthesia were included in the study. Dr Speech software was used for acoustic analysis; mean fundamental frequency (fo), jitter %, shimmer %, and noise to harmonic ratio (NHR) were objectively measured and recorded. Voice Handicap Index-10 (VHI-10) was used for positive self-reporting of the severity of vocal symptoms. GRBAS scale (G: Grade, R: Roughness, B: Breathiness, A: Asthenia, and S: Strain) was also used (by the same clinician) for clinic subjective evaluation. Patient age ranged from 33 to 55 years and mean patient age was 42 years. Mean duration of symptoms was 22 months (range 16-30). Mean postoperative follow-up time was 14 months (range 6-24). Unilateral MB was observed in all patients (2 left, 3 right). There was a significant improvement in objective and subjective assessment methods in all our patients after surgery. According to the results of our few patients, MBR offers a physiological and anatomical approach to the treatment of patients with MB. The outcomes of delicate microlaryngeal surgery are promising.

Perceptual, Aerodynamic and Acoustic Evaluation of Vocal Characteristics in Subjects With Obesity

Obesity has tripled since 1975 and affects health across many domains. Increasing body mass index increases the risk to the obese subject of many non-communicable diseases. The study evaluated the perceptive, aerodynamic, and acoustic parameters that characterize the voice of the obese population. Eighty adult subjects (40 participants in each obese and control group) aged 18-50 years were enrolled. The perceptual voice analysis was performed using the Consensus Auditory Perceptual Evaluation of Voice. The aerodynamic and acoustic voice analyses were performed using the MIR Spiro lab instrument and Doctor's Speech software. A digital stopwatch was also used to measure maximum phonation time. Statistical analysis revealed a significant difference (P-value <0.05 and t value >2) between two groups on acoustic parameters, specifically Normalized noise energy and fundamental frequency tremor (F0 tremor). Normalized noise energy and fundamental frequency tremor were greater in the obese group. Moreover, maximum phonation time and expiratory reserve volume were significantly reduced in the obese group. Results of the present study showed poor voice quality and reduced expiratory reserve volume in obese individuals. This could be credited to the adverse effects of accrued adipose on the functioning of the laryngeal and respiratory systems. Increasing body mass index escalates the risk to the obese subjects of many non-communicable diseases.

EVALUATION OF THE MOBILE LEARNING APPLICATIONS THAT CAN BE USED TO DEVELOP ENGLISH LANGUAGE SKILLS AMONG STUDENTS WITH BLINDNESS IN THE INCLUSIVE CLASS

This study aimed to evaluate the mobile applications that can be used in the inclusive classroom to teach and enhance English language skills among students with blindness. The analytical research design was employed in the current study. Using specific keywords and criteria, a total of 64 Voice Recognition Software (VRS), 31 Optical Character Recognition software (OCR), 34 Text to Speech software (TTS), and 59 e-Dictionaries available in android platform from January to August 2021 were analyzed using accessibility and usability checklist prepared by the authors. The tool's validity and consistency were gained through experts' good judgment and following the inter-rater reliability method. The findings of the study revealed that Google Assistant, Google Translator, SayHi Translator, and Talking Translator were ranked first among the VRS and e-Dictionaries, so they are considered as the best VRS and e-Dictionaries available in android platform that can be used to develop vocabulary and speaking skills among students with blindness. Whereas, Scanner Go, Clear Scanner, vFlat, Documents Scanner, Google Lens and Fast Scan Apps were ranked first among the OCR software. However, T2S, @Voice, Google Lens, and TTS Reader Apps were ranked first among the TTS Apps and considered as the best free TTS Apps available in android platform. Therefore, they are highly recommended to be used by general teachers in inclusive settings to compensate the lack of special technology, adapt the English subject curriculum for students with blindness, and enhance the students' self-learning and participation in the English class.

IoT based Wireless Notice Board Using Raspberry Pi

Information dissemination using digital notice board plays an imperative role in this digital world. This work is primarily aimed at developing a wireless information board for displaying and broadcasting the announcements and notices that the user sends from the Internet using the IOT technology. By providing a sufficient power supply, the Raspberry Pi, node MCU and LED display work properly and the display is controlled by the android application. The application can be used by connecting it to the internet and this enables the admin to send the information from wherever in the planet and could be visualized in a matter of seconds. The admin uses the app by setting the correct username and password for WIFI. For sending information, PC or mobile phone are utilised and at recipient end, raspberry Pi is connected to the Web. The admin can send the data in the form of text or voice, which in turn would be displayed on the distant noticeboard. The LED display is to display the text/voice that the user has sent and the speaker is to announce the received text message. The displaying text would be scrolling in the display. By using the text to speech software, announcement the text that is scrolling on the LED screen become possible. Earlier the Wi-Fi notification board had been used and thereby experiencing a limit on coverage. In this proposed method, the Internet is used as a means of communication and no coverage problem exists.

Research on the Function of Visual Phonetic Software Praat in Vocational English Phonetics Teaching

Phonetics teaching is the most difficult part of English majors in higher vocational colleges. Many students are affected by their mother tongue pronunciation habits and the lack of systematic voice training at the middle school stage, resulting in weak phonetic foundations. There are problems such as inability to correctly distinguish between long and short vowels, voiced consonants, emphasized and light pronunciation, and intonation. To this end, the introduction of the visual speech software Praat, using its visual and intuitive image characteristics can assist teachers in class, help students find the pronunciation errors in time and correct them in time. Based on this, this article will combine the status quo of English phonetics teaching in higher vocational colleges and analyze the role of Praat phonetics learning software in phonetics teaching and its specific application implementation.

To Compare and Evaluate Laryngeal Changes in Patients with Dysphonia in Laryngopharyngeal Reflux (LPR) before and after Treatment with Proton Pump Inhibitors (PPI) and Prokinetic Drugs.

To evaluate and compare pre and post treatment results using the following parameters by (a) Dual probe pH monitoring. (b) Laryngeal mucosal changes as assessed by direct video laryngoscopy/stroboscopy using Belafsky scores. (c) Voice changes by using GRBAS and Dr Speech software for speech analysis. In our study we have evaluated and compared voice and laryngeal changes in patients with dysphonia and RSI > 10 (which is suggestive of LPR) before treatment and after 6months of treatment with Tab. Pantoprazole and Tab. Mosapride. This prospective study was carried out on 50 patients attending the ENT OPD of a tertiary care referral centre over a period of 18months i.e. from Nov 2008 to Apr 2010. The study showed that prolonged therapy (> 6months) is required to treat LPR effectively and 24h ambulatory dual probe pH metry and videolaryngoscopy to assess RFS are the most preferred diagnostic tools in LPR. Dr Speech software for voice analysis can give an objective assessment of voice changes in LPR before and after treatment. The treatment consisting of PPI and prokinetic drugs proved to be effective in laryngopharyngeal reflux disease as improvement was seen in all the parameters including reflux findings score, subjective and objective voice assessment. According to results of our study, 24h ambulatory dual probe pH metry, Reflux Finding Score (RFS), subjective and objective acoustic parameters can be used as indicators of efficacy of treatment.

Towards Assisting the Visually Impaired: A Review on Techniques for Decoding the Visual Data From Chart Images

The textual data of a document is supplemented by the graphical information in it. To make communication easier, they contain tables, charts and images. However, it excludes a section of our population - the visually impaired. With technological advancements, the blind can access the documents through text to speech software solutions. In this method, even images can be conveyed by reading out the figure captions. However, charts and other statistical comparisons which involve critical information are difficult to be “read” out this way. Aim of this paper is to analyse various methods available to solve this vexatious issue. We survey the state-of-the-art works that do the exact opposite of graphing tools. In this paper, we explore the existing literature in understanding the graphs and extracting the visual encoding from them. We classify these approaches into modality-based approaches, conventional and deep-learning based methods. The survey also contains comparisons and analyses relevant study datasets. As an outcome of this survey, we observe that: (i) All existing works under each category need decoding in a variety of graphs. (ii) Among the approaches, deep learning performs remarkably well in localisation and classification. However, it needs further improvements in reasoning from chart images. (iii) Research works are still in progress to access data from vector images. Recreating data from the raster images has unresolved issues. Based on this study, the various applications of decoding the graphs, challenges and future possibilities are also discussed. This paper explores current works in the extraction of chart data, which seek to enable researchers in Human Computer Interaction to achieve human-level perception of visual data by machines. In this era of visual summarisation of data, the AI approaches can automate the underlying data extraction and hence provide the natural language descriptions to support visually disabled users.

Effects of voiced consonants and speaker gender on the acoustic characteristics of preceding vowels in Ika

This article examines if the voicing of a consonant in Ika has any influence on the acoustic features of a preceding vowel. Ika (ISO 639-3 ikk) has nine vowels and this work centres on them. Nine pairs of words beginning with Ika vowels (the vowels preceding either voiced or voiceless consonants) were produced and analysed using the praat speech software. The acoustic characteristics (duration, fundamental frequency, first formant and second formant) of the initial vowels were investigated. Duration is measured in milliseconds (msec), fundamental frequency (F0), first formant (F1) and second formant (F2) are measured in hertz. The effects of voicing and speaker gender on these characteristics were observed. The results showed that the effects of voicing on the characteristics of the vowels were not statistically significant (p > 0.05). Although vowels preceding voiced consonants generally manifested longer durations and had lower F1 values, the ANOVA test conducted did not show significance at 5% probability. However, there were highly significant differences (p < 0.001) between the female and male speakers in the F0 and F1 values, with the female values being higher than the male values. Worthy of note is the result on the characteristics of the vowel /ɪ/ in voiced consonant environments as all the respondents (male and female) had equal values in all the acoustic characteristics analysed. This is an outstanding finding for an under studied language like Ika Igbo.

Acoustic Analysis of Voice in Laryngopharyngeal Cancers Pre and Post Radiotherapy.

Laryngopharyngeal cancers are one of the most commonly diagnosed head and neck malignancies frequently presenting primarily with change in voice. Radiotherapy being the main modality of treatment for early cancers continues to affect voice. Hence, acoustic analysis of the voice offers quantifiable values of several parameters delineating the obvious effect of the therapy. A total number of 60 patients, diagnosed with laryngopharyngeal cancers undergoing radiotherapy underwent acoustic voice assessment using Dr. speech software pre-treatment and at 1 and 3months post radiotherapy. Data analysis was done using Mann-Whitney test and Wilcoxon signed rank test and a significant p value was obtained. The results of the study showed fundamental frequency (F0) and noise to harmonic ratio (NHR) to be the most affected in comparison to Jitter and Shimmer. The F0 and NHR values across baseline evaluation, first month and third month follow up showed a steady deterioration which was significant. The deterioration noted from the first to third month was not statistically significant. Across genders both F0 and NHR deterioration is more in males than in females. Radiotherapy causes definitive alterations in some acoustic measures of voice, which make the voice disharmonic and hoarse with contribution of harshness and breathiness. The effect is more pronounced on vocal parameters that are structure and projection based as evidenced by deterioration in values noted in F0 and NHR. Persistent deteriorated acoustic parameters for a longer duration of time are more likely which emphasizes the need for early voice rehabilitation.