Voice Restoration and Quality of Life in Larynx Cancer

Alaryngeal Speech Enhancement for Noisy Environments Using a Pareto Denoising Gated LSTM

Loss of the larynx significantly alters natural voice production, requiring alternative communication modalities and rehabilitation methods to restore speech intelligibility and improve the quality of life of affected individuals. This paper explores advances in alaryngeal speech enhancement to improve signal quality and reduce background noise, focusing on individuals who have undergone laryngectomy. In this study, speech samples were obtained from 23 Lithuanian males who had undergone laryngectomy with secondary implantation of the tracheoesophageal prosthesis (TEP). Pareto-optimized gated long short-term memory was trained on tracheoesophageal speech data to recognize complex temporal connections and contextual information in speech signals. The system was able to distinguish between actual speech and various forms of noise and artifacts, resulting in a 25% drop in the mean signal-to-noise ratio compared to other approaches. According to acoustic analysis, the system significantly decreased the number of unvoiced frames (proportion of voiced frames) from 40% to 10% while maintaining stable proportions of voiced frames (proportion of voiced speech frames) and average voicing evidence (average voice evidence in voiced frames), indicating the accuracy of the approach in selectively attenuating noise and undesired speech artifacts while preserving important speech information.

The Localisation of a Tracheoesophageal Shunt during Laryn(-gopharyn)gectomy Determines the Risk of Shunt Insufficiency

BACKGROUND

Tracheoesophageal shunt insufficiency (TESI) is a common and potentially life-threatening complication after laryn(-gopharyn)gectomy (L(P)E). We investigated whether TESI could be the result of a specific shunt location.

METHODS

A monocentric, retrospective cohort analysis of 171 consecutively treated L(P)E patients was performed. Patients with a secondary prosthesis instillation and patients with insufficient postoperative imaging were excluded. Disease related data as well as location of primary voice prosthesis were assessed.

RESULTS

The cohort was divided into 62 TESI-positive and 109 TESI-negative individuals. The mean time from surgery to TESI was 32 months. No differences were observed in gender, age, tumor localization, T/R/M-status. Surgery without adjuvant therapy was more often performed in TESI-negative individuals when compared with their positive counterparts. However, Cox regression including T/N status, therapy and categorized distance of the tracheoesophageal shunt to the manubrium (≤1.5 cm vs. >1.5 cm) revealed that a distance of ≤1.5 cm was associated with a 2.1-fold increased risk of TESI, while all other parameters did not influence the event-free survival.

CONCLUSIONS

Primary shunt positioning ≤1.5 cm to the ridge of the manubrium is associated with an increased risk of TESI. In these individuals secondary shunt operation resulting in a position >1.5 cm distant to the manubrium should be recommended.