Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Doi, Hironori; Nakamura, Keigo; Toda, Tomoki; Saruwatari, Hiroshi; Shikano, Kiyohiro

doi:10.1587/transinf.e93.d.2472

Cited by 25 publications

(14 citation statements)

References 9 publications

(13 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7, it is obvious that SensorD performs significantly better than using Sensor data alone across both Type I and Type II intraoral devices. Similar trends where SensorD is superior over Sensor were also reported in [7]. In addition, the Type II intraoral design outperformed its counterpart (i.e.…”

Section: Evaluation Of the Intraoral Devicessupporting

confidence: 79%

“…On the other hand, typing-based augmented and alternative communication (AAC) devices are limited by slow manual text input [5]. Although some improvements have been achieved in term of the voice quality of the electrolarynx and esophageal speech [6,7], emerging assistive technologies (ATs) such as silent speech interfaces (SSIs) have shown promising potential in recent years as an alternate solution. SSIs are devices that enable speech communication to take place in the absence of audible acoustic signals [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Towards an Intraoral-Based Silent Speech Restoration System for Post-laryngectomy Voice Replacement

Cheah

Gilbert

González

et al. 2017

Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

Abstract. Silent Speech Interfaces (SSIs) are alternative assistive speech technologies that are capable of restoring speech communication for those individuals who have lost their voice due to laryngectomy or diseases affecting the vocal cords. However, many of these SSIs are still deemed as impractical due to a high degree of intrusiveness and discomfort, hence limiting their transition to outside of the laboratory environment. We aim to address the hardware challenges faced in developing a practical SSI for post-laryngectomy speech rehabilitation. A new Permanent Magnet Articulography (PMA) system is presented which fits within the palatal cavity of the user's mouth, giving unobtrusive appearance and high portability. The prototype is comprised of a miniaturized circuit constructed using commercial off-the-shelf (COTS) components and is implemented in the form of a dental retainer, which is mounted under roof of the user's mouth and firmly clasps onto the upper teeth. Preliminary evaluation via speech recognition experiments demonstrates that the intraoral prototype achieves reasonable word recognition accuracy and is comparable to the external PMA version. Moreover, the intraoral design is expected to improve on its stability and robustness, with a much improved appearance since it can be completely hidden inside the user's mouth. [8]. To date, a number of SSIs have been proposed in an attempt to extract non-acoustic information generated during speech production and reproduce audible speech using different sensing modalities, such as measuring electrical activities of the brain [9][10][11] or the articulator muscles [12][13][14], or by capturing movements of the speech articulators themselves [3,5,8,[15][16][17][18][19]. A comprehensive summary on different SSIs technologies were presented in [8]. Because of their unique feature, SSIs can also be deployed in acoustically challenging environment or where privacy/confidentially is desirable, and not limited to its use as a communication aid for speech impaired individuals. KeywordsDespite the attractive attributes of SSIs, there are still challenges in the form of hardware (e.g. portability, lightweight, unobtrusiveness and wearability) and processing software (e.g. efficiency, robustness and intelligibility speech generation). Preliminary discussions on the influential factors affecting the SSIs' implementation were presented in [8], based upon criteria such as ability to operate in silence and noisy environments, usability by laryngectomees, issue of invasiveness market reediness and cost.In the present work we employ the Permanent Magnet Articulography (PMA), which is a type SSI that is based on sensing the changes in the magnetic field generated by a set of permanent magnet markers attached onto the vocal apparatus (i.e. lips and tongue) during speech articulation by using an array of magnetic sensors located around the mouth [1,3]. Although PMA shares some similarities with Electromagnetic Articulography (EMA) [5,17], it does not explicitly provide the ...

show abstract

Section: Evaluation Of the Intraoral Devicessupporting

confidence: 79%

Section: Introductionmentioning

confidence: 99%

Towards an Intraoral-Based Silent Speech Restoration System for Post-laryngectomy Voice Replacement

Cheah

Gilbert

González

et al. 2017

Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

show abstract

“…Whereas, typing-based augmented and alternative communication (AAC) devices are limited by slow manual text input (Wang et al, 2012). Although some improvements were achieved in term of voicing quality of the electrolarynx and oesophageal speech (Doi et al, 2010;Toda et al, 2012), emerging assistive technologies (ATs) such as silent speech interfaces (SSIs) have shown promising potential in recent years as an alternate solution.…”

Section: Introductionmentioning

confidence: 99%

Preliminary Evaluation of a Silent Speech Interface based on Intra-Oral Magnetic Sensing

Cheah

Bai

González

et al. 2016

Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies

View full text Add to dashboard Cite

This paper addresses the hardware challenges faced in developing a practical silent speech interface (SSI) for post-laryngectomy speech rehabilitation. Although a number of SSIs have been developed, many are still deemed as impractical due to a high degree of intrusiveness and discomfort, hence limiting their transition to outside of the laboratory environment. The aim of this paper is to build upon our previous work, in developing a user-centric prototype and enhancing its desirable features. A new Permanent Magnet Articulography (PMA) system is presented which fits within the palatal cavity of the user's mouth, giving unobtrusive appearance and high portability. The prototype is comprised of a miniaturised circuit constructed using commercial off-the-shelf (COTS) components and is implemented in the form of a dental retainer, which is mounted under roof of the user's mouth and firmly clasps onto the upper teeth. Preliminary evaluation via speech recognition experiments demonstrates that the intraoral prototype achieves word recognition accuracy of 75.7%, slightly lower than its predecessor. Nonetheless, the intraoral design is expected to improve the stability and robustness of the PMA system with a much improved appearance since it can be completely hidden inside the user's mouth.

show abstract

“…In addition, the tracheo-esophageal option requires an additional surgery, which is not suitable for every patient (Bailey et al, 2006). Although research is being conducted on improving the voice quality of esophageal or electrolarynx speech (Doi et al, 2010;Toda et al, 2012), new assistive technologies based on non-audio information (e.g., visual or articulatory information) may be a good alternative approach for providing natural sounding speech output for persons after laryngectomy.…”

Section: Introductionmentioning

confidence: 99%

Preliminary Test of a Real-Time, Interactive Silent Speech Interface Based on Electromagnetic Articulograph

Wang¹,

Samal²,

Green³

2014

Proceedings of the 5th Workshop on Speech and Language Processing for Assistive Technologies

View full text Add to dashboard Cite

A silent speech interface (SSI) maps articulatory movement data to speech output. Although still in experimental stages, silent speech interfaces hold significant potential for facilitating oral communication in persons after laryngectomy or with other severe voice impairments. Despite the recent efforts on silent speech recognition algorithm development using offline data analysis, online test of SSIs have rarely been conducted. In this paper, we present a preliminary, online test of a real-time, interactive SSI based on electromagnetic motion tracking. The SSI played back synthesized speech sounds in response to the user's tongue and lip movements. Three English talkers participated in this test, where they mouthed (silently articulated) phrases using the device to complete a phrase-reading task. Among the three participants, 96.67% to 100% of the mouthed phrases were correctly recognized and corresponding synthesized sounds were played after a short delay. Furthermore, one participant demonstrated the feasibility of using the SSI for a short conversation. The experimental results demonstrated the feasibility and potential of silent speech interfaces based on electromagnetic articulograph for future clinical applications.

show abstract

Esophageal Speech Enhancement Based on Statistical Voice Conversion with Gaussian Mixture Models

Cited by 25 publications

References 9 publications

Towards an Intraoral-Based Silent Speech Restoration System for Post-laryngectomy Voice Replacement

Towards an Intraoral-Based Silent Speech Restoration System for Post-laryngectomy Voice Replacement

Preliminary Evaluation of a Silent Speech Interface based on Intra-Oral Magnetic Sensing

Preliminary Test of a Real-Time, Interactive Silent Speech Interface Based on Electromagnetic Articulograph

Contact Info

Product

Resources

About