The use of speech recognition technology by people living with amyotrophic lateral sclerosis: a scoping review

BACKGROUND

More than 80% of people living with Amyotrophic Lateral Sclerosis (plwALS) develop difficulties with their speech, affecting communication, self-identity and quality of life. Automatic speech recognition technology (ASR) is becoming a common way to interact with a broad range of devices, to find information and control the environment.ASR can be problematic for people with acquired neurogenic motor speech difficulties (dysarthria). Given that the field is rapidly developing, a scoping review is warranted.

AIMS

This study undertakes a scoping review on the use of ASR technology by plwALS and identifies research gaps in the existing literature.

MATERIALS AND METHODS

Electronic databases and relevant grey literature were searched from 1990 to 2020. Eleven research papers and articles were identified that included participants living with ALS using ASR technology. Relevant data were extracted from the included sources, and a narrative summary of the findings presented.Outcomes and Results: Eleven publications used recordings of plwALS to assess word recognition rate (WRR) word error rate (WER) or phoneme error rate (PER) and appropriacy of responses by ASR devices. All were found to be linked to severity of dysarthria and the ASR technology used. One article examined how speech modification may improve ASR accuracy. The final article completed thematic analysis of Amazon.com reviews for the Amazon Echo and plwALS were reported to use ASR devices to control the environment and summon assistance.

CONCLUSIONS

There are gaps in the evidence base: understanding expectations of plwALS and how they use ASR technology; how WER/PER/WRR relates to usability; how ASR use changes as ALS progresses.Implications for rehabilitationDevices that people can interact with using speech are becoming ubiquitous. As movement and mobility are likely to be affected by ALS and progress over time, speech interaction could be very helpful for accessing information and environmental control.However, many people living with ALS (plwALS) also have impaired speech (dysarthria) and experience trouble using voice interaction technology because it may not understand them.Although advances in automated speech recognition (ASR) technology promise better understanding of dysarthric speech, future research needs to investigate how plwALS use ASR, how accurate it needs to be to be functionally useful, and how useful it may be over time as the disease progresses.

Acceptance and Commitment Therapy for people living with motor neuron disease: an uncontrolled feasibility study

BACKGROUND

Motor neuron disease (MND) is a fatal, progressive neurodegenerative disease that causes progressive weakening and wasting of limb, bulbar, thoracic and abdominal muscles. Clear evidence-based guidance on how psychological distress should be managed in people living with MND (plwMND) is lacking. Acceptance and Commitment Therapy (ACT) is a form of psychological therapy that may be particularly suitable for this population. However, to the authors' knowledge, no study to date has evaluated ACT for plwMND. Consequently, the primary aim of this uncontrolled feasibility study was to examine the feasibility and acceptability of ACT for improving the psychological health of plwMND.

METHODS

PlwMND aged ≥ 18 years were recruited from 10 UK MND Care Centres/Clinics. Participants received up to 8 one-to-one ACT sessions, developed specifically for plwMND, plus usual care. Co-primary feasibility and acceptability outcomes were uptake (≥ 80% of the target sample [N = 28] recruited) and initial engagement with the intervention (≥ 70% completing ≥ 2 sessions). Secondary outcomes included measures of quality of life, anxiety, depression, disease-related functioning, health status and psychological flexibility in plwMND and quality of life and burden in caregivers. Outcomes were assessed at baseline and 6 months.

RESULTS

Both a priori indicators of success were met: 29 plwMND (104%) were recruited and 76% (22/29) attended ≥ 2 sessions. Attrition at 6-months was higher than anticipated (8/29, 28%), but only two dropouts were due to lack of acceptability of the intervention. Acceptability was further supported by good satisfaction with therapy and session attendance. Data were possibly suggestive of small improvements in anxiety and psychological quality of life from baseline to 6 months in plwMND, despite a small but expected deterioration in disease-related functioning and health status.

CONCLUSIONS

There was good evidence of acceptability and feasibility. Limitations included the lack of a control group and small sample size, which complicate interpretation of findings. A fully powered RCT to evaluate the clinical and cost-effectiveness of ACT for plwMND is underway.

TRIAL REGISTRATION

The study was pre-registered with the ISRCTN Registry (ISRCTN12655391).

Voice banking for people living with motor neurone disease: Views and expectations

BACKGROUND

More than 80% of people living with MND (plwMND) develop difficulties with their speech, affecting communication, self-identity and quality of life. Most plwMND eventually use an augmentative and alternative communication device (AAC) to communicate. Some AAC devices provide a synthesized voice for speech, however these voices are often viewed as impersonal and a factor in AAC acceptance. Voice banking creates an approximation of the person's own voice that can be used in AAC and is argued to go some way to preserve a person's identity when natural voice is lost, but there has been little supporting research.

AIMS

To understand what plwMND consider when deciding whether or not to bank their voice, what their expectations are, and the expectations of significant communication partners.

METHODS

Semi-structured interviews were undertaken with plwMND who had either decided to bank their voice or had decided not to. Thematic analysis was used to provide a qualitative analysis of the data.

PROCEDURES

Participants were an opportunistic sample of plwMND within England recruited via an open advert distributed by the MND Association (MNDA).

OUTCOMES AND RESULTS

Twelve plwMND were interviewed with nine significant others. Nine participants had decided to bank their voice and three decided not to. The data suggest 'preserving identity' is the overarching motivation in decision making for voice banking. Participants who decided to voice bank considered it would help to maintain their identity and preserve their social and work networks. Participants deciding not to bank their voice highlighted it could not replace their natural voice or preserve their identity. However, few in either group showed an awareness of how a voice bank is used in AAC, and how communication using AAC is significantly different to natural speech.

CONCLUSIONS AND IMPLICATIONS

This research is the first study of its kind to examine the considerations for decision making around voice banking for plwMND. Preserving identity is central to decision making when considering whether or not to voice bank. However, the reality of using AAC and voice banking for communication is poorly understood. Professionals have a role to provide plwMND with more information about voice banking in the wider context of using AAC for communication. It may be that the process of voice banking itself is seen as a positive act for plwMND, independent of how it is used later. Further research with associated professionals and stakeholders is indicated. What this paper adds What is already known on this subject Voice banking creates an approximation of the person.s own voice that can be used in AAC, and is argued to go some way to preserve a person's identity when natural voice is lost. There is significant and growing interest in voice banking from the MND community, but there has been little supporting research. What this study adds This research is the first study of its kind to examine decision making surrounding voice banking. It shows how preserving identity is critically important in how people deal with a diagnosis of MND. For those choosing to voice bank, it is seen as an effective way of preserving their identity, a way of 'fighting back' and giving a positive psychological benefit. Those deciding against voice banking do not believe it could maintain their identity and cannot bring back the natural voice they once had. Clinical implications of this study The reality of using AAC and voice banking for communication may be poorly understood. It would be helpful for professionals to provide information about voice banking as part of a wider discussion about the range of options for communication as the condition progresses. It is important that this includes the opportunity to listen to a voice bank to support understanding of how it is used in a communication device, and how different it sounds to natural speech.

The Question of Data Integrity in Article-Level Metrics

Interest in and use of article-level metrics (ALMs) has grown rapidly amongst the research community, by researchers, publishers, funders, and research institutions. As this happens, it is critical to ensure secure and reliable data that is trustworthy and can be used by all. Two case studies are presented, which illustrate different approaches to establishing ALM data integrity.

Effects of submaximal cycling and long-term endurance training on neutrophil phagocytic activity in middle aged men

OBJECTIVE

To investigate the effects of long term (> 10 years) endurance training and submaximal exercise on the phagocytic activity of circulating neutrophil granulocytes.

METHODS

The ability of stimulated blood neutrophils isolated from well trained cyclists [n = 8; VO2max 61.0(SD 8.8) ml.kg-1.min-1; age 38(4) years] and age matched sedentary controls [n = 8; VO2max 37.4 (6.6) ml.kg-1.min-1] to ingest nitroblue tetrazolium was assessed at rest and following a standardised submaximal bout of exercise on a cycle ergometer.

RESULTS

Trained subjects had a lower resting blood neutrophil count (P < 0.01). Acute exercise caused a rise (P < 0.01) in the blood neutrophil count irrespective of training status, but the magnitude of the rise was smaller in the trained subjects (P < 0.05). The circulating neutrophil phagocytic capacity was approximately 70% lower in trained individuals at rest compared with the control subjects (P < 0.01). Acute submaximal exercise increased this variable in both groups, but phagocytic capacity remained substantially lower in the trained subjects compared with the controls (P < 0.05) despite the observation that a higher proportion of the circulating neutrophils were stimulated to undergo phagocytosis in the trained subjects [57(14)% v 32(7)%; P < 0.01).

CONCLUSIONS

Although neutrophil phagocytic activity is only one variable that contributes to immunological status, prolonged periods of endurance training may lead to increased susceptibility to opportunistic infections by diminishing this activity at rest.

Cardiorespiratory, hormonal and haematological responses to submaximal cycling performed 2 days after eccentric or concentric exercise bouts

Eccentric muscle actions are known to induce delayed-onset muscle soreness (DOMS) and muscle weakness (reduced static strength and dynamic peak power output) that may persist for several days. The aim of the present study was to determine whether DOMS-inducing exercise affects physiological responses to subsequent submaximal dynamic exercise. Physiological and metabolic responses to a standardized exercise task were measured 2 days after the performance of an eccentric or concentric exercise bout. Six healthy, untrained male subjects aged 30 +/- 7 years (mean +/- S.D.) performed repeated eccentric contractions during 30 min of bench stepping (47-cm step, 15 steps min-1). On another occasion, they performed concentric contractions by walking uphill (8% incline) for 30 min at 5 km h-1, which elicited a similar heart rate response to bench stepping. Two days after the eccentric or concentric exercise, the subjects cycled for 15 min on an electrically braked cycle ergometer at a work rate (172 +/- 37 W) equivalent to 80% VO2 max. The order of the preceding treatments was randomized and the treatments were carried out 2 weeks apart. Two days after the eccentric exercise, all subjects reported leg muscle soreness and exhibited elevated levels of serum creatine kinase activity (P < 0.01) and plasma cortisol concentration (P < 0.05). After uphill walking, the subjects were not sore and serum creatine kinase activity was unchanged. Minute volume, breathing frequency, respiratory exchange ratio, heart rate, rating of perceived exertion, venous blood lactate concentration and plasma cortisol concentration were all higher (P < 0.05) during cycling after eccentric exercise compared with after uphill walking. Increases in plasma catecholamine concentrations and numbers of circulating leucocytes after cycling at 80% VO2 max for 15 min were similar under both experimental conditions, but the delayed leucocytosis (at 150 min post-exercise) was significantly greater (P < 0.01) for the post-eccentric exercise condition. We conclude that dynamic submaximal exercise performed 2 days following exercise with a large eccentric component produces physiological responses that are indicative of a higher relative exercise stress. It is likely that such effects will significantly limit the level and duration of exercise that can be achieved in subsequent training bouts over several days.

Short-term changes in the blood leucocyte and platelet count following different durations of high-intensity treadmill running

Short-term changes in the blood leucocyte count after exercise are known to be dependent on the intensity of exercise performed. The aim of the present study was to investigate the effects of the duration of high-intensity exercise on changes in the leucocyte and platelet count during the early recovery period. On separate occasions following a standard warm-up, eight healthy subjects (six males, two females) ran at a constant speed of 5.6 m s-1 (20 km h-1) on a level treadmill for 30, 60, 90, 120 or 150 s or to fatigue. Heart rates were increased to near maximal levels within 30 s of exercise. Significant increases in the blood leucocyte count occurred after all exercise durations compared with baseline (pre-exercise) levels. Running for 30 s increased the blood leucocyte count by 35 +/- 10% (x +/- S.D.). Running for 60 s increased the blood leucocyte count by 57 +/- 16%, but running for longer durations did not produce any further significant increase in the immediately post-exercise blood leucocyte count. After exercise to exhaustion, the leucocyte count had increased by 63 +/- 17%. This was mainly due to an increase of lymphocytes (114 +/- 20%) rather than neutrophils (34 +/- 7%). At exhaustion, plasma volume had decreased by 15.9 +/- 2.6% compared with pre-exercise. During 5 min of recovery from exercise, the leucocyte count fell significantly (after 30 and 60 s of running), remained unchanged (90 and 120 s) or increased significantly (150 s and fatigue) compared with immediately post-exercise.(ABSTRACT TRUNCATED AT 250 WORDS)

Haematological and acute-phase responses associated with delayed-onset muscle soreness in humans

Delayed-onset muscle soreness following unaccustomed or eccentric exercise is associated with inflammation, tissue necrosis and the release of muscle enzymes (Newham et al. 1983). We have investigated the time course of changes in circulating leucocytes and serum levels of some acute phase reactants, serum creatine kinase activity (CK) and muscle pain after a 40-min bout of bench-stepping exercise in eight healthy untrained subjects. Leg muscle soreness was greatest 2 days after the exercise bout. Peak serum CK values [mean (SD) 540 (502) IU.1-1] occurred 1-7 days post-exercise. Serum C-reactive protein (CRP) was unchanged from pre-exercise levels [7.8 (3.4) mg.1-1] immediately post-exercise [7.9 (2.3) mg.1-1] but rose to a peak of 17.0 (3.9) mg.1-1 1 day post-exercise, thereafter declining to basal levels. Serum levels of iron and zinc fell below pre-exercise levels for 1-3 days post-exercise. Serum albumin, IgG and IgM fell below pre-exercise levels from 1 day post-exercise, reaching minimal values (about 80% of basal levels) at 7 days post-exercise. The exercise did not appear to significantly affect serum levels of alpha-1-antitrypsin and alpha-1-acid glycoprotein. Two and three days after the exercise bout the circulating numbers of total leucocytes, neutrophils, monocytes and basophils fell 15-20% below pre-exercise levels, whereas lymphocytes, eosinophils and platelets were unchanged. The results indicate that a rapid acute phase inflammatory response is initiated within 1 day of a bout of exercise that induces delayed-onset muscle soreness, and that any later tissue necrosis that may occur is not accompanied by further marked changes in acute-phase reactants such as CRP.