During Lipreading Training With Sentence Stimuli, Feedback Controls Learning and Generalization to Audiovisual Speech in Noise

2021 ◽  
pp. 1-21
Author(s):  
Lynne E. Bernstein ◽  
Edward T. Auer ◽  
Silvio P. Eberhardt
Keyword(s):  
Speech Recognition ◽  
Word Recognition ◽  
Perceptual Learning ◽  
Correct Response ◽  
Incorrect Response ◽  
Visual Speech ◽  
Control Group ◽  
Feedback Controls ◽  
Open Set ◽  
Percentage Points

Purpose: This study investigated the effects of external feedback on perceptual learning of visual speech during lipreading training with sentence stimuli. The goal was to improve visual-only (VO) speech recognition and increase accuracy of audiovisual (AV) speech recognition in noise. The rationale was that spoken word recognition depends on the accuracy of sublexical (phonemic/phonetic) speech perception; effective feedback during training must support sublexical perceptual learning. Method: Normal-hearing (NH) adults were assigned to one of three types of feedback: Sentence feedback was the entire sentence printed after responding to the stimulus. Word feedback was the correct response words and perceptually near but incorrect response words. Consonant feedback was correct response words and consonants in incorrect but perceptually near response words. Six training sessions were given. Pre- and posttraining testing included an untrained control group. Test stimuli were disyllable nonsense words for forced-choice consonant identification, and isolated words and sentences for open-set identification. Words and sentences were VO, AV, and audio-only (AO) with the audio in speech-shaped noise. Results: Lipreading accuracy increased during training. Pre- and posttraining tests of consonant identification showed no improvement beyond test–retest increases obtained by untrained controls. Isolated word recognition with a talker not seen during training showed that the control group improved more than the sentence group. Tests of untrained sentences showed that the consonant group significantly improved in all of the stimulus conditions (VO, AO, and AV). Its mean words correct scores increased by 9.2 percentage points for VO, 3.4 percentage points for AO, and 9.8 percentage points for AV stimuli. Conclusions: Consonant feedback during training with sentences stimuli significantly increased perceptual learning. The training generalized to untrained VO, AO, and AV sentence stimuli. Lipreading training has potential to significantly improve adults' face-to-face communication in noisy settings in which the talker can be seen.

Masking Level Differences for Tones and Speech in Elderly Listeners With Relatively Normal Audiograms

1994 ◽  
Vol 37 (2) ◽  
pp. 422-428 ◽  
Author(s):  
John H. Grose ◽  
Elizabeth A. Poth ◽  
Robert W. Peters
Keyword(s):  
Hearing Loss ◽  
Speech Recognition ◽  
Word Recognition ◽  
The Elderly ◽  
Normal Hearing ◽  
The Other ◽  
Control Group ◽  
Central Effects ◽  
Masking Level Difference ◽  
Tone Detection

This study measured the masking level difference (MLD) for both 500-Hz tone detection and spondee word recognition in two groups of listeners. One group consisted of 9 elderly listeners with normal audiometric sensitivity bilaterally, up to at least 2000 Hz. The other group was a control group of 10 young listeners with normal hearing. The intent was to determine whether the elderly listeners exhibited a reduction in binaural performance that might contribute to the difficulties many such listeners have in understanding speech in noisy situations. By measuring MLDs in elderly listeners in the absence of marked peripheral hearing loss, it was hoped that any observed changes in MLD could be more strongly attributed to central effects. For both tone detection and speech recognition, it was found that the elderly performed more poorly than the young listeners, primarily on the NoSπ condition.

Effect of Various Visual Speech Units on Language Identification Using Visual Speech Recognition

2020 ◽  
Vol 20 (04) ◽  
pp. 2050029
Author(s):  
Aparna Brahme ◽  
Umesh Bhadade
Keyword(s):  
Speech Recognition ◽  
Word Recognition ◽  
Language Model ◽  
Recognition Rate ◽  
Spoken Language ◽  
Language Identification ◽  
Visual Speech ◽  
Language Recognition ◽  
Language Discrimination ◽  
Visual Speech Recognition

In this paper, we describe our work in Spoken language Identification using Visual Speech Recognition (VSR) and analyze the effect of various visual speech units used to transcribe the visual speech on language recognition. We have proposed a new approach of word recognition followed by the word N-gram language model (WRWLM), which uses high-level syntactic features and the word bigram language model for language discrimination. Also, as opposed to the traditional visemic approach, we propose a holistic approach of using the signature of a whole word, referred to as a “Visual Word” as visual speech unit for transcribing visual speech. The result shows Word Recognition Rate (WRR) of 88% and Language Recognition Rate (LRR) of 94% in speaker dependent cases and 58% WRR and 77% LRR in speaker independent cases for English and Marathi digit classification task. The proposed approach is also evaluated for continuous speech input. The result shows that the Spoken Language Identification rate of 50% is possible even though the WRR using Visual Speech Recognition is below 10%, using only 1[Formula: see text]s of speech. Also, there is an improvement of about 5% in language discrimination as compared to traditional visemic approaches.

scholarly journals Influence of Postponed Follow-Up after Cochlear Implant Activation during the COVID-19 Pandemic on Aided Sound Field Detection and Speech Recognition

2021 ◽  
pp. 1-8
Author(s):  
Teresa G. Vos ◽  
Kevin D. Brown ◽  
Emily Buss ◽  
Andrea L. Bucker ◽  
Matthew M. Dedmon ◽  
...  
Keyword(s):  
Speech Recognition ◽  
Word Recognition ◽  
Cochlear Implant ◽  
Sound Field ◽  
Control Group ◽  
Field Detection ◽  
Tertiary Referral Center ◽  
Behavioral Thresholds ◽  
Comfort Levels

<b><i>Introduction:</i></b> The objective of this study was to assess the influence of postponing the first post-activation follow-up due to the COVID-19 pandemic on the aided sound field detection thresholds and speech recognition of cochlear implant (CI) users. <b><i>Methods:</i></b> A retrospective review was performed at a tertiary referral center. Two groups of adult CI recipients were evaluated: (1) patients whose first post-activation follow-up was postponed due to COVID-19 closures (postponed group; <i>n</i> = 10) and (2) a control group that attended recommended post-activation follow-ups prior to the COVID-19 pandemic (control group; <i>n</i> = 18). For both groups, electric thresholds were estimated at initial activation based on comfort levels and were measured behaviorally at subsequent post-activation follow-ups. For the control group, behavioral thresholds were measured at the 1-month follow-up. For the postponed group, behavioral thresholds were not measured until 3 months post-activation since the 1-month follow-up was postponed. The aided pure-tone average (PTA) and word recognition results were compared between groups at the 3-month follow-up and at an interim visit 2–9 weeks later. <b><i>Results:</i></b> At the 3-month follow-up, the postponed group had significantly poorer word recognition (23 vs. 42%, <i>p</i> = 0.027) and aided PTA (42 vs. 37 dB HL, <i>p</i> = 0.041) than the control group. No significant differences were observed between 3-month data from the control group and interim data from the postponed group. <b><i>Conclusions:</i></b> The postponed follow-up after CI activation was associated with poorer outcomes, both in terms of speech recognition and aided audibility. However, these detrimental effects were reversed following provision of an individualized map, with behaviorally measured electric threshold and comfort levels. While adult CI recipients demonstrate an improvement in speech recognition with estimated electric thresholds, the present results suggest that behavioral mapping within the initial weeks of device use may support optimal outcomes.

Asynchrony modeling for audio-visual speech recognition

2002 ◽  
Author(s):  
Guillaume Gravier ◽  
Gerasimos Potamianos ◽  
Chalapathy Neti
Keyword(s):  
Speech Recognition ◽  
Visual Speech ◽  
Visual Speech Recognition

Long-Term Follow-Up of Early Cochlear Implant Device Activation

2021 ◽  
pp. 1-11
Author(s):  
Stefanie Bruschke ◽  
Uwe Baumann ◽  
Timo Stöver
Keyword(s):  
Speech Recognition ◽  
Side Effects ◽  
Cochlear Implant ◽  
Surgical Techniques ◽  
Control Group ◽  
First Year ◽  
Safe Procedure ◽  
Sound Processor

Background: The cochlear implant (CI) is a standard procedure for the treatment of patients with severe to profound hearing loss. In the past, a standard healing period of 3–6 weeks occurred after CI surgery before the sound processor was initially activated. Advancements of surgical techniques and instruments allow an earlier initial activation of the processor within 14 days after surgery. Objective: Evaluation of the early CI device activation after CI surgery within 14 days, comparison to the first activation after 4–6 weeks, and assessment of the feasibility and safety of the early fitting over a 12 month observation period were the objectives of this study. Method: In a prospective study, 127 patients scheduled for CI surgery were divided into early fitting group (EF, n = 67) and control group (CG, n = 60). Individual questionnaires were used to evaluate medical and technical outcomes of the EF. Medical side effects, speech recognition, and follow-up effort were compared with the CG within the first year after CI surgery. Results: The early fitting was feasible in 97% of the EF patients. In the EF, the processor was activated 25 days earlier than in the CG. No major complications were observed in either group. At the follow-up appointments, side effects such as pain and balance problems occurred with comparable frequency in both groups. At initial fitting, the EF showed a significantly higher incidence of medical minor complications (p < 0.05). When developing speech recognition within the first year of CI use, no difference was observed. Furthermore, the follow-up effort within the first year after CI surgery was comparable in both groups. Conclusions: Early fitting of the sound processor is a feasible and safe procedure with comparable follow-up effort. Although more early minor complications were observed in the EF, there were no long-term wound healing problems caused by the early fitting. Regular inspection of the magnet strength is recommended as part of the CI follow-up since postoperative wound swelling must be expected. The early fitting procedure enabled a clear reduction in the waiting time between CI surgery and initial sound processor activation.

Maximizing Cochlear Implant Outcomes with Short-Term Aural Rehabilitation

2021 ◽  
Author(s):  
Claire Marcus Bernstein ◽  
Diane Majerus Brewer ◽  
Matthew H. Bakke ◽  
Anne D. Olson ◽  
Elizabeth Jackson Machmer ◽  
...  
Keyword(s):  
Clinical Study ◽  
Speech Recognition ◽  
Cochlear Implant ◽  
Active Control ◽  
Analysis Of Variance ◽  
Control Group ◽  
Active Control Group ◽  
Short Term ◽  
Aural Rehabilitation ◽  
Profound Deafness

Abstract Background Increasing numbers of adults are receiving cochlear implants (CIs) and many achieve high levels of speech perception and improved quality of life. However, a proportion of implant recipients still struggle due to limited speech recognition and/or greater communication demands in their daily lives. For these individuals a program of aural rehabilitation (AR) has the potential to improve outcomes. Purpose The study investigated the effects of a short-term AR intervention on speech recognition, functional communication, and psychosocial outcomes in post lingually deafened adult CI users. Research Design The experimental design was a multisite clinical study with participants randomized to either an AR treatment or active control group. Each group completed 6 weekly 90-minute individual treatment sessions. Assessments were completed pretreatment, 1 week and 2 months post-treatment. Study Sample Twenty-five post lingually deafened adult CI recipients participated. AR group: mean age 66.2 (48–80); nine females, four males; months postactivation 7.7 (3–16); mean years severe to profound deafness 18.4 (2–40). Active control group: mean age 62.8 (47–85); eight females, four males; months postactivation 7.0 (3–13); mean years severe to profound deafness 18.8 (1–55). Intervention The AR protocol consisted of auditory training (words, sentences, speech tracking), and psychosocial counseling (informational and communication strategies). Active control group participants engaged in cognitive stimulation activities (e.g., crosswords, sudoku, etc.). Data Collection and Analysis Repeated measures ANOVA or analysis of variance, MANOVA or multivariate analysis of variance, and planned contrasts were used to compare group performance on the following measures: CasperSent; Hearing Handicap Inventory; Nijmegen Cochlear Implant Questionnaire; Client Oriented Scale of Improvement; Glasgow Benefit Inventory. Results The AR group showed statistically significant improvements on speech recognition performance, psychosocial function, and communication goals with no significant improvement seen in the control group. The two groups were statistically equivalent on all outcome measures at preassessment. The robust improvements for the AR group were maintained at 2 months post-treatment. Conclusion Results of this clinical study provide evidence that a short-term AR intervention protocol can maximize outcomes for adult post lingually deafened CI users. The impact of this brief multidimensional AR intervention to extend CI benefit is compelling, and may serve as a template for best practices with adult CI users.

scholarly journals The Efficacy of Anti-Arrhythmic Drugs in Children With Idiopathic Frequent Symptomatic or Asymptomatic Premature Ventricular Complexes With or Without Asymptomatic Ventricular Tachycardia: a Retrospective Multi-Center Study

2021 ◽  
Author(s):  
Robin A. Bertels ◽  
Janneke A. E. Kammeraad ◽  
Anna M. Zeelenberg ◽  
Luc H. Filippini ◽  
Ingmar Knobbe ◽  
...  
Keyword(s):  
Ventricular Tachycardia ◽  
Beta Blockers ◽  
Control Group ◽  
Premature Ventricular Complexes ◽  
Percentage Points ◽  
Asymptomatic Children ◽  
Group A ◽  
The Mean ◽  
Multi Center Study ◽  
Center Study

AbstractThe aim of the study is to compare the efficacy of flecainide, beta-blockers, sotalol, and verapamil in children with frequent PVCs, with or without asymptomatic VT. Frequent premature ventricular complexes (PVCs) and asymptomatic ventricular tachycardia (VT) in children with structurally normal hearts require anti-arrhythmic drug (AAD) therapy depending on the severity of symptoms or ventricular dysfunction; however, data on efficacy in children are scarce. Both symptomatic and asymptomatic children (≥ 1 year and < 18 years of age) with a PVC burden of 5% or more, with or without asymptomatic runs of VT, who had consecutive Holter recordings, were included in this retrospective multi-center study. The groups of patients receiving AAD therapy were compared to an untreated control group. A medication episode was defined as a timeframe in which the highest dosage at a fixed level of a single drug was used in a patient. A total of 35 children and 46 medication episodes were included, with an overall change in PVC burden on Holter of -4.4 percentage points, compared to -4.2 in the control group of 14 patients. The mean reduction in PVC burden was only significant in patients receiving flecainide (− 13.8 percentage points; N = 10; p = 0.032), compared to the control group and other groups receiving beta-blockers (− 1.7 percentage points; N = 18), sotalol (+ 1.0 percentage points; N = 7), or verapamil (− 3.9 percentage points; N = 11). The efficacy of anti-arrhythmic drug therapy on frequent PVCs or asymptomatic VTs in children is very limited. Only flecainide appears to be effective in lowering the PVC burden.

Sign in / Sign up

Export Citation Format

Share Document