Prediction of larynx function using multichannel surface EMG classification

Total laryngectomy (TL) affects critical functions such as swallowing, coughing and speaking. An artificial, bio-engineered larynx (ABL), operated via myoelectric signals, may improve quality of life for TL patients. To evaluate the efficacy of using surface electromyography (sEMG) as a control signal to predict instances of swallowing, coughing and speaking, sEMG was recorded from submental, intercostal and diaphragm muscles. The cohort included TL and control participants. Swallowing, coughing, speaking and movement actions were recorded, and a range of classifiers were investigated for prediction of these actions. Our algorithm achieved F1-scores of 76.0 ± 4.4 % (swallows), 93.8 ± 2.8 % (coughs) and 70.5 ± 5.4 % (speech) for controls, and 67.7 ± 4.4 % (swallows), 71.0 ± 9.1 % (coughs) and 78.0 ± 3.8 % (speech) for TLs, using a random forest (RF) classifier. 75.1 ± 6.9 % of swallows were detected within 500 ms of onset in the controls, and 63.1 ± 6.1 % in TLs. sEMG can be used to predict critical larynx movements, although a viable ABL requires improvements. Results are particularly encouraging as they encompass a TL cohort. An ABL could alleviate many challenges faced by laryngectomees. This study represents a promising step toward realising such a device.

Sense of Effort and Fatigue Associated With Talking After Total Laryngectomy

PURPOSE

Sense of effort and fatigue associated with talking was compared in individuals with and without a total laryngectomy.

METHOD

An online survey of individuals using tracheoesophageal speech (TES; n = 222), electrolaryngeal speech (ELS; n = 132), esophageal speech (n = 41), and laryngeal speech (LS; n = 112) asked about 3 domains of effort when talking: frequency of occurrence, withdrawal from talking, and location in the body. Three aspects of fatigue were explored: frequency of occurrence, fatigue type, and duration of talking before fatigue.

RESULTS

Alaryngeal groups reported significantly more talking-related effort and fatigue than the LS group. Sixty-three percent of all respondents indicated that effort caused them to talk less, with no group differences on this item. Significantly more effort was localized to the lips and tongue by ELS compared with TES and LS groups. Both the ELS and TES groups had higher shoulder/arm effort when talking compared with the esophageal speech and LS groups. ELS respondents reported less fatigue than the TES group. When fatigue was present, the TES group had more physical and less mental fatigue than the ELS group. The duration of talking before experiencing fatigue was significantly shorter for the alaryngeal groups compared with the LS group.

CONCLUSIONS

Effort and fatigue associated with talking are a common report for individuals using alaryngeal speech. The location of effort within the body and the type of fatigue experienced vary to some extent across alaryngeal speaking methods.

Chest Wall Kinematics during Speech Breathing in Tracheoesophageal Speakers

Objectives:

The purpose of the present study was to determine how tracheoesophageal (TE) speakers manipulate the chest wall (rib cage and abdomen) to speak and how respiratory compromise (chronic obstructive pulmonary disease; COPD) and task variables influence those behaviors.

Methods:

The chest wall movements of 11 male TE speakers (5 with COPD and 6 without COPD) were measured during tidal breathing, spontaneous speech, and reading. Repeated-measures multivariate analyses were used to compare breathing behaviors across speech tasks and by respiratory health. Additional repeated-measures multivariate analyses and 1-way analyses of variance were conducted on temporal, aerodynamic, and linguistic measures.

Results:

There was a significant main effect of task and a significant interaction effect of COPD and task on chest wall movements. Rib cage movements varied by task, whereas abdominal movements were as predicted. There was a significant difference in utterance length by task. There were no main effects of COPD on the chest wall and no significant group differences in utterance length, aerodynamic measures, or intelligibility. The TE speakers were generally accurate in inspiring at appropriate linguistic boundaries.

Conclusions:

The results suggest that there is robust control for speech breathing following laryngectomy, but that there is also increased effort within the chest wall. Implications for future research considerations are discussed.

Lung Volumes Used during Speech Breathing in Tracheoesophageal Speakers

Objectives:

The purpose of this study was to determine how tracheoesophageal (TE) speakers manipulate lung volumes to meet speech demands and how respiratory compromise (chronic obstructive pulmonary disease [COPD]) and task variables influence these behaviors.

Methods:

The lung volumes of 9 male TE speakers (4 with COPD, 5 without) during tidal breathing, spontaneous speech, and reading were investigated. Repeated-measures multivariate analyses of variance were used to compare lung volumes and utterance length across speech tasks and by respiratory health. A one-way analysis of variance was used to compare aerodynamic measures and intelligibility by COPD diagnosis.

Results:

There was a significant main effect of task and a significant interaction effect of COPD and task on lung volumes at initiation and termination of speech. The TE speakers terminated speech exclusively below the resting expiratory level (REL) in both speech tasks because of elevated RELs, which are often present after laryngectomy. There were no main effects of COPD on any lung volume measures and no significant group differences in utterance length, aerodynamic measures, or intelligibility.

Conclusions:

Intelligibility and aerodynamic measures were not influenced by lung volumes and were comparable to findings of previous research. Speaking past the REL might be a compensation to optimize expiratory control for speech in a compromised system and a marker for the increased effort often anecdotally described by TE speakers.

Speech breathing in speakers who use an electrolarynx

Speakers who use an electrolarynx following a total laryngectomy no longer require pulmonary support for speech. Subsequently, chest wall movements may be affected; however, chest wall movements in these speakers are not well defined. The purpose of this investigation was to evaluate speech breathing in speakers who use an electrolarynx during speech and reading tasks. Six speakers who use an electrolarynx underwent an evaluation of chest wall kinematics (e.g., chest wall movements, temporal characteristics of chest wall movement), lung volumes, temporal measures of speech, and the interaction of linguistic influences on ventilation. Results of the present study were compared to previous reports in speakers who use an electrolarynx, as well as to previous reports in typical speakers. There were no significant differences in lung volumes used and the general movement of the chest wall by task; however, there were differences of note in the temporal aspects of chest wall configuration when compared to previous reports in both typical speakers and speakers who use an electrolarynx. These differences were related to timing and posturing of the chest wall. The lack of differences in lung volumes and chest wall movements by task indicates that neither reading nor spontaneous speech exerts a greater influence on speech breathing; however, the temporal and posturing results suggest the possibility of a decoupling of the respiratory system from speech following a total laryngectomy and subsequent alaryngeal speech rehabilitation.

LEARNING OUTCOMES

The reader will be able to understand and describe: (1) The primary differences in speech breathing across alaryngeal speech options; (2) how speech breathing specifically differs (i.e., lung volumes and chest wall movements) in speakers who use an electrolarynx; (3) How the coupling of speech and respiration is altered when pulmonary air is no longer used for speech.

The effects of a total laryngectomy on speech breathing

PURPOSE OF REVIEW

Alaryngeal speech rehabilitation following a total laryngectomy is a multifactorial disorder that includes changes in phonation, respiration, and overall general health. Tracheoesophageal speech is the preferred method of rehabilitation. In this approach, pulmonary air support is diverted from the trachea into the esophagus to generate voicing. Tracheoesophageal speakers must overcome radical upper airway changes, increased resistance in the phonatory source, reduced sensory feedback from the respiratory system, and probable respiratory compromise. This review integrates previous laryngectomy research with recent studies investigating kinematics in tracheoesophageal speakers.

RECENT FINDINGS

Tracheoesophageal speakers are often very intelligible and communicate effectively, but little has been done to investigate the physiological demands of tracheoesophageal speech on speakers. Two recent studies have specifically investigated speech breathing behaviors in tracheoesophageal speakers. Both investigations reported increased effort and differences in speech breathing compared to laryngeal speakers; however, continued research is needed to understand the effects of a total laryngectomy on speech breathing.

SUMMARY

The physiological changes following a laryngectomy, especially in the ability to produce tracheoesophageal speech, are not well known. Rehabilitation for these individuals requires an understanding of the changes in respiration that might influence speech breathing behaviors.