Abstract
This paper surveys the uses of non-speech voice as an interaction modality within sonic applications. Three main contexts of use have been identified: sound retrieval, sound synthesis and control, and sound design. An overview of different choices and techniques regarding the style of interaction, the selection of vocal features and their mapping to sound features or controls is here displayed. A comprehensive collection of examples instantiates the use of non-speech voice in actual tools for sonic interaction. It is pointed out that while voice-based techniques are already being used proficiently in sound retrieval and sound synthesis, their use in sound design is still at an exploratory phase. An example of creation of a voice-driven sound design tool is here illustrated.
Highlights
The voice is the primary communication channel among humans
Such definition represents an issue in the first place: A semi-automatic classification, performed for instance by machine learning algorithms relying on generic audio features, is likely to produce different categories than a classification built on perceptual basis [4]
In a sound synthesizer controlled via singing voice [31], descriptors are extracted from the vocal signal via Shorttime Fourier Transform (STFT) and classified in four groups related to their use for control: Excitation (F0 and energy), Vocal Tract, Voice Quality and Context
Summary
The voice is the primary communication channel among humans. While speech is considered to be the most important form of voice communication, non-speech voice as well is a means to convey a wide array of information. Mimicking and imitating sounds are typical actions that are intuitively performed by means of non-speech voice They require no production or recollection of verbal information and provided that adequate techniques to match the voice to the sounds are made available, vocal imitation is a potentially effective and immediate retrieval strategy. While a structured use of non-speech voice in such context is still missing, partly due to the lack of an engineered approach to the discipline, past and present research focus on exploiting non-speech voice to perform fast prototyping in sonic interaction and to facilitate the communication of audio concepts.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
