Speech Aid Research Articles

Speech Aid Prostheses For Patients With Cleft and Other Craniofacial Birth Conditions.

Normal speech production is a complex mechanism requiring the coordination of several organs of the oral cavity. The lip, hard and soft palates, and teeth all play a role in normal speech production. In cases of craniofacial birth conditions such as cleft lip and palate or ectodermal dysplasia, one or more of these areas may be compromised. Surgical correction is the most ideal means to provide normalcy but surgery may not always be appropriate or possible. In such cases, a speech aid prosthesis may serve as an interim or definitive way to normalize speech. This article describes the several options that may be employed toward this end.

Predicting the intelligibility of Mandarin Chinese with manipulated and intact tonal information for normal-hearing listeners.

Objective indices for predicting speech intelligibility offer a quick and convenient alternative to behavioral measures of speech intelligibility. However, most such indices are designed for a specific language, such as English, and they do not take adequate account of tonal information in speech when applied to languages like Mandarin Chinese (hereafter called Mandarin) for which the patterns of fundamental frequency (F0) variation play an important role in distinguishing speech sounds with similar phonetic content. To address this, two experiments with normal-hearing listeners were conducted examining: (1) The impact of manipulations of tonal information on the intelligibility of Mandarin sentences presented in speech-shaped noise (SSN) at several signal-to-noise ratios (SNRs); (2) The intelligibility of Mandarin sentences with intact tonal information presented in SSN, pink noise, and babble at several SNRs. The outcomes were not correctly predicted by the Hearing Aid Speech Perception Index (HASPI-V1). A new intelligibility metric was developed that used one acoustic feature from HASPI-V1 plus Hilbert time envelope and temporal fine structure information from multiple frequency bands. For the new metric, the Pearson correlation between obtained and predicted intelligibility was 0.923 and the root mean square error was 0.119. The new metric provides a potential tool for evaluating Mandarin intelligibility.

Result of consistent use of hearing aid in speech and language development.

Objective: To determine the benefits of proper guidance and proper use of hearing aid in language development age. Study Design: Descriptive Cross-sectional study. Setting: Department of ENT, Abbasi Shaheed Hospital and Karachi Medical and Dental College. Period: January 2022 to December 2023. Methods: In this study those cases were included which came with hearing loss. Both sexes were included in this study. After informed consent complete history and examination was done. Also relevant investigations were performed where required. Results: In this study, male were 72 (60%), male female ratio was 1.5:1. Highest number of patients were between the age of 6-8 years 60 (50%). Between 1.5 to 3 years, 51 children were properly guided and followed the proper instruction of use of hearing aid while 9 children were not properly guided and not properly used of hearing aid. 92 patients (76.6%) used hearing aid consistent with proper guidance, in which 79 (85.8%) children developed good speech and language. while 13 (14.1%) children were found poor in speech and language development while 28 (23.33%) children did not use hearing aid properly and all found poor in speech and language. Conclusion: Proper use of hearing aid which may be beneficial in improvement of word recognition and speech development in hearing impaired child under proper guidance and training from otologist and audiologist.

The Noise Reduction Algorithm May Not Compensate for the Degradation in Output Signal-to-Noise Ratio Caused by Wide Dynamic Range Compression.

Most modern hearing aids (HAs) employ wide dynamic range compression (WDRC) and noise reduction (NR) algorithms. It is known that the nonlinear effects of WDRC and NR cause changes to the output signal-to-noise ratio (SNR) of an HA. However, the relative contributions of WDRC and NR to the nonlinear effects are not fully understood. The current study investigated (a) whether WDRC or NR dominates the nonlinear effects measured at the output of a digital HA and (b) whether the electroacoustic effectiveness of NR depends on WDRC parameters while input SNR and background noise are systematically varied. Test stimuli were Connected Speech Test sentences in multitalker babble noise (2- or 20-talker), presented at input SNRs ranging from -10 to +10 dB. The HA was programmed using multiband WDRC set according to the National Acoustic Laboratories for Nonlinear HA fitting formula 2 prescriptive fits for four standard audiograms and two compression speeds. The NR algorithm of the HA was switched on or off in separate conditions. Nonlinear electroacoustic effects from the WDRC and NR algorithms were assessed by measuring the output SNR of the HA using a phase-inversion technique. To investigate whether there are other factors that may be important besides the output SNR, the Hearing Aid Speech Intelligibility Index and the Hearing Aid Speech Quality Index were applied to the recordings to generate inferences on aided speech intelligibility and perceived speech quality. Results showed that WDRC dominated the net nonlinear effect at low-input SNRs, and the net nonlinear effect of WDRC and NR was reduced at high-input SNRs. Results also showed that the effectiveness of NR depended on compression parameters. The effectiveness of NR was partially explained by the trend of Hearing Aid Speech Intelligibility Index and Hearing Aid Speech Quality Index scores, potentially indicating that the Hearing Aid Speech Intelligibility Index and Hearing Aid Speech Quality Index scores may capture factors that cannot be captured by the output SNR metric. Results suggest that the individual signal-processing stages in an HA should not be considered as independent. Electroacoustic evaluation of WDRC and NR algorithms in isolation is not sufficient to capture the combined nonlinear effect of the two algorithms. https://doi.org/10.23641/asha.25962541.

Behaviour settings as a way to order types of situations for the study of speech aids.

This article revisits the notion of behaviour settings, coined by Roger G. Barker (Barker 1968, Ecol. Psychol. 28, 39-55 (10.1080/10407413.2016.1121744)), as a useful concept for the analysis of situations and communicative needs of persons after larynx removal surgery (laryngectomy). We claim that behaviour settings offer a way to characterize types of situations and types of participation, which, in turn, helps to identify aspects of communication where compensation is needed; these steps are crucial in the design process of reliable and context-sensitive speech aids. Moreover, we advocate complementing the behaviour setting concept as a unit of analysis with modern developments in the cognitive sciences, such as conversational analysis of co-operative actions (Goodwin 2017, Co-operative action (learning in doing: social, cognitive and computational perspectives). Cambridge: Cambridge University Press (10.1017/9781139016735)) and the analysis of multi-perspectival experience (De Jaegher 2021, Phenomenol. Cogn. Sci. 20, 847-870 (10.1007/s11097-019-09634-5)). Such an integration of macro- and micro-level patterns should help discover the relevant relations and values in particular situations. We illustrate our claims with examples from Barker's own work and from our ongoing analyses of the everyday life of persons after laryngectomy. This article is part of the theme issue 'People, places, things, and communities: expanding behaviour settings theory in the twenty-first century'.

A technique of speech aid adjustment with the assistance of nasalance values for non-nasal and nasal sounds

Evaluation of speech function is essential to maxillofacial prosthetic treatment. Measurement of nasalance with a nasometer is practical and typically done to detect hypernasality in maxillofacial defect patients. This case report describes a nasalance test used in the evaluation and rehabilitation of a patient who needed a speech aid. A 70-year-old man sought help at our clinic because his old speech aid had broken. Although a new speech aid was fabricated, he continued to have difficulty speaking and breathing. A nasalance test using nasal and non-nasal test words revealed hyponasality. The patient was satisfied with the speech aid after its adjustment in accordance with the nasalance test results. Nasalance testing that considers not only hypernasality but hyponasality helped the maxillofacial prosthodontist in the successful rehabilitation of this maxillofacial defect patient. (Int J Maxillofac Prosthetics 2020;3:23-27)

A Comprehensive Study on Mental Illness Through Speech and EEG Using Artificial Intelligence


 A typical mental ailment is depression that considerably harms an individual's everyday activities as well as their mental health. In light of the fact that mental health is one of the biggest problems facing society, researchers have been looking into several strategies for efficiently identifying depression. Mental illness can now be identified through speech analysis thanks to modern artificial intelligence. The speech aids in classifying a patient's mental health status, which could benefit their new study. For the purpose of identifying depression or any other emotion or mood in an individual, a number of past studies based on machine learning and artificial intelligence are being studied. The study also examines the effectiveness of facial expression, photos, emotional chatbots, and texts in identifying a person's emotions. Naive-Bayes, Support Vector Machines (SVM), Linear Support Vectors, Logistic Regression, etc. are ML approaches from text processing. Artificial Neural Network (ANN) is a sort of artificial intelligence method used to extract information from photos and classify them in order to recognise emotions from facial expressions.

Delay-constrained hearing aid speech enhancement using a wireless remote microphone

Hearing aids have been shown in literature to offer better noise reduction and spatial cue preservation when used alongside a remote microphone. Oftentimes, this is in ideal conditions where both devices are synchronized and can transmit data losslessly and instantaneously. In practice, hearing aids tend to receive remote microphone data via wireless link, which incurs a slew of adverse effects. Among these, transmission delay is of particular importance, as hearing aids already have tight constraints on allowable end-to-end delay. Typically, this delay constraint is under 10 ms for perceptual reasons. In this work, we study a filter designed for hearing aids with a network-delayed remote microphone. Originally, the filter is derived and analyzed in the time frequency domain without explicit consideration of the delay constraints. We rederive the filter to address this gap, and seek to measure the effect of the network delay and delay constraints on overall performance.

Speech-derived haptic stimulation enhances speech recognition in a multi-talker background

Speech understanding, while effortless in quiet conditions, is challenging in noisy environments. Previous studies have revealed that a feasible approach to supplement speech-in-noise (SiN) perception consists in presenting speech-derived signals as haptic input. In the current study, we investigated whether the presentation of a vibrotactile signal derived from the speech temporal envelope can improve SiN intelligibility in a multi-talker background for untrained, normal-hearing listeners. We also determined if vibrotactile sensitivity, evaluated using vibrotactile detection thresholds, modulates the extent of audio-tactile SiN improvement. In practice, we measured participants’ speech recognition in a multi-talker noise without (audio-only) and with (audio-tactile) concurrent vibrotactile stimulation delivered in three schemes: to the left or right palm, or to both. Averaged across the three stimulation delivery schemes, the vibrotactile stimulation led to a significant improvement of 0.41 dB in SiN recognition when compared to the audio-only condition. Notably, there were no significant differences observed between the improvements in these delivery schemes. In addition, audio-tactile SiN benefit was significantly predicted by participants’ vibrotactile threshold levels and unimodal (audio-only) SiN performance. The extent of the improvement afforded by speech-envelope-derived vibrotactile stimulation was in line with previously uncovered vibrotactile enhancements of SiN perception in untrained listeners with no known hearing impairment. Overall, these results highlight the potential of concurrent vibrotactile stimulation to improve SiN recognition, especially in individuals with poor SiN perception abilities, and tentatively more so with increasing tactile sensitivity. Moreover, they lend support to the multimodal accounts of speech perception and research on tactile speech aid devices.

Modified Multiple Stimulus With Hidden Reference and Anchors-Gabrielsson Total Impression Sound Quality Rating Comparisons for Speech in Quiet, Noise, and Reverberation.

The purpose of the study was to obtain, analyze, and compare subjective sound quality data for the same test stimuli using modified multistimulus MUSHRA (Multiple Stimulus with Hidden Reference and Anchors) based procedures (viz., MUSHRA with custom anchors and MUSHRA without anchor) and the single-stimulus Gabrielsson's total impression rating procedure. Twenty normally hearing young adults were recruited in this study. Participants completed sound quality ratings on two different hearing aid recording data sets-Data Set A contained speech recordings from four different hearing aids under a variety of noisy and processing conditions, and Data Set B contained speech recordings from a single hearing aid under a combination of different noisy, reverberant, and signal processing conditions. Recordings in both data sets were rated for their quality using the total impression rating procedure. In addition, quality ratings of Data Set A recordings were obtained using a MUSHRA with custom anchors, while the ratings of Data Set B recordings were collected using a MUSHRA without anchor. Statistical analyses revealed a high test-retest reliability of quality ratings for the same stimuli that were rated multiple times. In addition, high-interrater reliability was observed with all three rating procedures. Further analyses indicated (a) a high correlation between the total impression rating and the two modified MUSHRA ratings and (b) a similar relationship between the average and standard deviation of the subjective rating data obtained by the total impression rating and MUSHRA with custom anchors on Data Set A, and the total impression rating and the MUSHRA without anchor on Data Set B. Both sound quality procedures, namely, the MUSHRA-based procedures and the total impression rating scale, obtained similar quality ratings of varied hearing aid speech recordings with high reliability.

Modelling the language education at multicultural university environment

Introduction. Subject of the article is relevant due to new educational trends caused by challenges of the time. The authors have repeatedly addressed the problems of communicative asymmetry and concretization of the content of teaching foreign language communication. The importance of the problem demands the necessity of further develop of theoretical and methodological aspects of teaching students foreign language communication in multicultural educational space.Purpose setting. The research is aimed at creating the universal model of teaching foreign spoken language in various spheres of communication. Creating of communication learning model in a multicultural university environment requires solving some conceptual and practical tasks.Methodology and methods of the study. Theoretical and empirical methods were used: comparative analysis of scientific literature on the research problem; generalization of pedagogical experience; diagnostic methods.Results. The result of the research is the development of invariant and variable components of the model of learning foreign language communication. The invariant part of the model includes the definite hierarchy of communicative skills. The author promotes a logically consistent scheme for the development of receptive and concretized expressive skills at each level of communicative competence. The variable part of the model is of vital significance. This is the content of training, which includes linguistic material and speech aids, subject matter, a corpus of diverse texts. The model involves samples of creative tasks in accordance with the stages of development of communicative skills, as well as methodological comments.Conclusion. Analyzing theory and pedagogical experience and actual practices author reveals perspectives of realization of the learning model that provides more flexible process and effective level of foreign language training of future specialists. The materials of research and the author»s learning model represented and by invariant and variable components can be used in the framework of academic work with the students of different directions of training. The results of the study may be applied in modernization of the language education at multicultural university.

A Non-Intrusive speech quality evaluation algorithm for hearing aids via an auxiliary training task

With the increasing severity of hearing problems caused by an aging population, it has become more urgent to study speech quality evaluation methods for hearing aids to automatically judge the effect of parameter adjustments to solve the problem of lack of audiologists. A new evaluation algorithm, which is based on the multi-task learning strategy that combines the main task of non-intrusive speech quality evaluation with the auxiliary task of quality classification, is proposed. The main task network is composed of a bi-directional long short-term memory (BiLSTM) network combined with the self-attention mechanism, and the auxiliary task network is formed by fully connected layers based on batch normalization. The proposed algorithm firstly uses a convolutional neural network (CNN) to extract frame-level features. Then, the features are inputted into the main task network and the auxiliary task network to extract utterance-level features, respectively. Finally, the objective scores and quality ratings are obtained by the different mappers. Evaluation experiments of the Hearing Aid Speech Quality Index (HASQI) show that compared with others algorithms, the proposed algorithm effectively improves the speech quality evaluation. And it also shows strong robustness and good generalization performances under different distorted conditions.

Acoustic feedback control in hearing aids with frequency warping

Acoustic Feedback Control continues to be a challenging problem due to the emerging form factors in advanced hearing aids and hearables, especially for severe and profound losses. In order to mitigate the effects of feedback in hearing aids, we present a novel use of frequency warping called “Freping,” for manipulating signals in the frequency domain. Freping is a non-linear transformation which breaks the similarity between the input and acoustic feedback signals of a hearing aid to prevent feedback. In this work, we implemented Freping in realtime for feedback management, as well as novel techniques to preserve the naturalness of sound. Our prior work has shown that Freping improves Added Stable Gain (ASG) in the presence of feedback while maintaining the same Hearing Aid Speech Quality Index (HASQI). We present new results for feedback management with Freping by performing “on-ear” measurements on an acoustic KEMAR manikin using standard hearing aid verification systems. We conducted feedback tests to measure the ASG with various configurations of Freping for various hearing loss levels using the NAL-NL2 prescriptions on a realtime open-source speech processing system for hearing aids. We also compare Freping feedback performance with that of commercial hearing aids.

Influence of speech aid prosthesis with speech therapy on speech outcomes in adult patients with persisting velopharyngeal insufficiency: A retrospective analysis

Statement of problemProsthetic intervention with a speech aid prosthesis (SAP) along with speech therapy has been reported to improve speech outcomes in patients with persisting velopharyngeal insufficiency (VPI). However, little is known regarding the impact of this treatment on different speech parameters over time in adult patients with VPI. PurposeThe purpose of this retrospective study was to evaluate the change in speech parameters after rehabilitation with an SAP and speech therapy in adult patients with VPI using subjective and objective tests. Material and methodsPatients above 16 years of age who had received prosthetic treatment for VPI and had complete speech assessment records between 2017 and 2020 were included in the analysis. After completion of the prosthetic treatment, speech therapy comprising 2 sessions per week of 45 minutes was provided by a speech pathologist. Speech evaluation was performed using tests that included speech intelligibility calculation, nasal pinch test, audible nasal air emissions, acoustic analysis, and the nasalance check. Assessments were done at 4 time intervals: T0: without an SAP; T1: 1 week with an SAP; T2: 1 month with an SAP; and T3: 3 months with an SAP. A descriptive analysis was followed by a comparison between groups using the Friedman test for subjective assessments and repeated measures ANOVA for objective tests (α=.05). ResultsOf 10 individuals who had received an SAP, 5 participants, 2 men and 3 women with a mean age of 38 years were included in the analysis. Statistically significant improvement in mean scores was observed from T0 to T3 concerning speech intelligibility (P<.001), hypernasality (P<.001), audible nasal air emission (P<.001), mean fundamental frequency (P=.034), shimmer percentage (P=.004), and nasalance (P=.004). Improvement in jitter percentage was not statistically significant (P=.218). ConclusionsAn SAP along with speech therapy should be considered as a conservative and effective treatment option for addressing speech issues in adult patients with VPI.

An objective comparison of speech intelligibility and quality of hearing aid of different companies

Abstract Purpose: This study aimed to verify the intelligibility and quality of hearing aid-processed speech across companies through objective measures. The output of hearing aids programmed to different prescriptive formulae (Company fit, NAL NL 1, NAL NL 2, and DSLv5) across companies (Company I, Company II, Company III, Company IV, and Company V) were recorded and stored in the sound level meter connected to the manikin. Materials and Methods: Offline analysis of speech quality of the recorded speech was done using the Hearing Aid Speech Quality Index (HASQI), the intelligibilty was measured using the Hearing Aid Speech Perception Index (HASPI) and Speech Intelligibility Index (SII), and Long-Term Average Speech Spectrum (LTASS) was used to measure the spectral composition of speech. Results: When the companies are compared, the hearing aid of Company V showed significantly higher SII values for all prescriptive formulae indicative of better speech intelligibility provided by Company V hearing aids. In terms of speech quality, all the hearing aids showed similar HASQI values. Conclusions: The reasons for each of these findings are highlighted and recommendations for best practices on the use of objective measures for verifying the hearing aid output in clinical setups are suggested.

Robust intelligibility and quality evaluation of combined temporal and spectral processing for hearing impaired

• Combined temporal-spectral processing objectively evaluated in terms of HASQI and HASPI. • Six types of audiograms based on different slope and frequency losses are selected. • -5, -3, 0, 3, 5, 10 dB SNRs noisy environments in cafe, traffic, station and train are considered. • Proposed enhanced algorithm shows markable improvements in quality and intelligibility. Hearing-impaired people face numerous challenges with speech perception in the presence of interfering background noise. To suppress interfering background noise, the common approach widely used is speech enhancement. Inspired by the improved results of combined temporal and spectral processing in speech enhancement, this research study proposes temporal enhancement combined with two different spectral enhancement methods, with a novel approach of soft masking using priori and posterior signal to noise ratio uncertainty. The present study investigates quality and intelligibility objective evaluations, namely, hearing aid speech quality index and hearing aid speech perception index, of spectral and a combination of temporal-spectral speech enhancement methods for typical pattern of hearing loss characterized by six audiograms. For evaluation, clean speech files from the NOIZEUS database are mixed with four local noises, namely, cafeteria, traffic, station, and train at -5, -3, 0,3,5, and 10 dB SNRs. These local noises are quite common, which are encountered by people in their day-to-day lives. In most of the testing conditions, the new combined temporal spectral enhancement shows improved results in comparison with the purely spectral processing methods.

Seeing a talking face matters: Infants' segmentation of continuous auditory-visual speech.

Visual speech cues from a speaker's talking face aid speech segmentation in adults, but despite the importance of speech segmentation in language acquisition, little is known about the possible influence of visual speech on infants' speech segmentation. Here, to investigate whether there is facilitation of speech segmentation by visual information, two groups of English-learning 7-month-old infants were presented with continuous speech passages, one group with auditory-only (AO) speech and the other with auditory-visual (AV) speech. Additionally, the possible relation between infants' relative attention to the speaker's mouth versus eye regions and their segmentation performance was examined. Both the AO and the AV groups of infants successfully segmented words from the continuous speech stream, but segmentation performance persisted for longer for infants in the AV group. Interestingly, while AV group infants showed no significant relation between the relative amount of time spent fixating the speaker's mouth versus eyes and word segmentation, their attention to the mouth was greater than that of AO group infants, especially early in test trials. The results are discussed in relation to the possible pathways through which visual speech cues aid speech perception.

Inner speech as a cognitive tool—or what is the point of talking to oneself?

ABSTRACT Many higher cognitive tasks, such as problem-solving and deliberation are accompanied by the experience of an inner voice in our heads. In this paper, we develop the idea that our own inner speech supports these tasks. We approach the phenomenon of inner speech through a comparison with overt speech – a comparison that is suggested by a Vygotskian approach that focuses on how inner speech develops from overt speech during ontogeny. We argue for the cognitive potency of inner speech by hypothesizing that condensed inner speech may help reduce cognitive load; yet by being pragmatically expanded upon, inner speech may scaffold further cognitive accomplishments. More specifically, as we adopt a Vygotskian perspective, we begin by introducing his notion of internalization and examine in what way inner speech might be condensed. Then the question of whether inner speech is governed by the same pragmatic mechanisms that govern overt speech is posed and answered in the affirmative. We advocate the idea that inner speech aids deliberation due, to some degree, to the manner in which pragmatic principles governing overt speech are re-purposed in inner speech. We close by addressing two objections.

Read my lips: Artificial intelligence word-level arabic lipreading system

Lipreading is the ability to recognize words or sentences from the mouth movements of a speaking person. This process is also known as Visual Speech Recognition (VSR). Lipreading has two main advantages: facilitate communication for people with hearing or speaking problems and aid speech recognition in noisy environments. In this paper, we propose a lipreading computing system capable of recognizing ten common Arabic words by performing word extraction from the mouth movements. The system receives a video of a person uttering an Arabic word as an input and outputs the text of the predicted word. During the implementation stage of the proposed system, three deep learning and neural network architectures are alternatively used to train, validate, and test the system using a locally collected and preprocessed dataset. The dataset contains 1051 videos and will be made available upon request. Moreover, a voting model that combines the three architectures is proposed. The highest testing accuracy (i.e. 82.84%) is achieved by leveraging the voting model.

Predicting crowdfunding success with visuals and speech in video ads and text ads

PurposeFor the case of many content features, This paper aims to investigate which content features in video and text ads more contribute to accurately predicting the success of crowdfunding by comparing prediction models.Design/methodology/approachWith 1,368 features extracted from 15,195 Kickstarter campaigns in the USA, the authors compare base models such as logistic regression (LR) with tree-based homogeneous ensembles such as eXtreme gradient boosting (XGBoost) and heterogeneous ensembles such as XGBoost + LR.FindingsXGBoost shows higher prediction accuracy than LR (82% vs 69%), in contrast to the findings of a previous relevant study. Regarding important content features, humans (e.g. founders) are more important than visual objects (e.g. products). In both spoken and written language, words related to experience (e.g. eat) or perception (e.g. hear) are more important than cognitive (e.g. causation) words. In addition, a focus on the future is more important than a present or past time orientation. Speech aids (see and compare) to complement visual content are also effective and positive tone matters in speech.Research limitations/implicationsThis research makes theoretical contributions by finding more important visuals (human) and language features (experience, perception and future time). Also, in a multimodal context, complementary cues (e.g. speech aids) across different modalities help. Furthermore, the noncontent parts of speech such as positive “tone” or pace of speech are important.Practical implicationsFounders are encouraged to assess and revise the content of their video or text ads as well as their basic campaign features (e.g. goal, duration and reward) before they launch their campaigns. Next, overly complex ensembles may suffer from overfitting problems. In practice, model validation using unseen data is recommended.Originality/valueRather than reducing the number of content feature dimensions (Kaminski and Hopp, 2020), by enabling advanced prediction models to accommodate many contents features, prediction accuracy rises substantially.