Development of Electrolarynx by Multi-agent Technology and Mobile Devices for Prosody Control

Abstract

The feasibility of using a motion sensor to replace a conventional electrolarynx (EL) user interface was explored. A mobile phone motion sensor with multi-agent platform was used to investigate on/off and pitch frequency control capability. A very small battery operated ARM-based control unit was also developed to evaluate the motion sensor based user-interface. The control unit was placed on the wrist and the vibration device was placed against the throat using support bandage. Two different conversion methods were used for the forearm tilt angle to pitch frequency conversion: linear mapping method and F0 template-based method. A perceptual evaluation was performed with two well-trained normal speakers and ten subjects. The results of the evaluation study showed that both methods were able to produce better speech quality in terms of naturalness.

Generating tonal distinctions in Mandarin Chinese using an electrolarynx with preprogrammed tone patterns

“…Another possible tone-control interface could incorporate accelerometers or gyroscopes to detect EL movements or angles for tone selection. This may function similarly to the position-sensing capabilities of modern cameras and mobile phones, or the wrist-watch-based control of EL activation described by Matsui et al (2013).…”

“…Current EL devices have the capacity to modulate F 0 through several methods: applying varying amounts of finger pressure on a single button (e.g. Western Electric #5, Western Electric; TruTone EL, Griffin Laboratories); controlling expiration pressure from the neck stoma (Uemi et al, 1994); filtering electromyographic (EMG) signals obtained from neck muscle contractions (Goldstein et al, 2004); and adjusting forearm tilt movement (Matsui et al, 2013). These devices have allowed speakers to convey natural intonation patterns in English and Japanese with varying degrees of success; however, effects on the vocal rehabilitation of tonal languages have not yet been shown.…”

Development of a hands‐free electrolarynx for obtaining a human‐like voice using the LPC residual wave

“…During these 20 years, many a research has been done on hands-free artificial larynx with a transducer worn on the neck. [2][3][4][5][6] There is also research on hands-free EL with sound start and stop detected using myopotential (EMG) sensors. [7][8][9][10] However, neither technology has been developed into wide practical use.…”

Voicing decision based on phonemes classification and spectral moments for whisper-to-speech conversion

“…Such system imposes a constant voicing while articulating, which may thus limit naturalness and intelligibility of unvoiced segments. Solutions to activate voicing manually based on finger or arm movements were proposed [5,6], yet not suitable to control rapid alternation between voiced and unvoiced segments that occur in normal speech. Therefore, automatic signal-based approaches to voicing decision have been broadly adopted in recent systems, many of which tackling whisper-to-speech (W2S) conversion tasks [7,8,9,10,11,12,13].…”