This article has multiple issues. Please help improve it or discuss these issues on the talk page. (Learn how and when to remove these template messages) This article relies largely or entirely on a single source. Relevant discussion may be found on the talk page. Please help improve this article by introducing citations to additional sources.Find sources: "Airstream mechanism" – news · newspapers · books · scholar · JSTOR (January 2010) This article includes a list of general references, but it lacks sufficient corresponding inline citations. Please help to improve this article by introducing more precise citations. (January 2010) (Learn how and when to remove this template message) (Learn how and when to remove this template message)

In phonetics, the airstream mechanism is the method by which airflow is created in the vocal tract. Along with phonation and articulation, it is one of three main components of speech production. The airstream mechanism is mandatory for most sound production and constitutes the first part of this process, which is called initiation.

The organ generating the airstream is called the initiator and there are three initiators used phonemically in non-disordered human oral languages:

There are also methods of making sounds that do not require the glottis. These mechanisms are collectively called alaryngeal speech mechanisms (none of these speech mechanisms are used in non-disordered speech):

Percussive consonants are produced without any airstream mechanism.[4]

Types of airstream mechanism

[4]Any of the three principal initiators − diaphragm, glottis or tongue − may act by either increasing or decreasing the pressure generating the airstream. These changes in pressure often correspond to outward and inward airflow, and are therefore termed egressive and ingressive respectively.

Of these six resulting airstream mechanisms, five are found lexically around the world:

These mechanisms may be combined into airstream contours, such as clicks which release into ejectives.

In normal vocabulary, the various Khoisan languages have pulmonic, ejective, and click consonants; the Chadic languages, some Mayan languages, and scattered Nilo-Saharan languages such as Gumuz, Uduk and Meʼen have pulmonic, implosive, and ejective consonants, and the Nguni languages of the Bantu family utilize all four, – pulmonic, click, implosive, and ejective, – as does the Dahalo language of Kenya. Most other languages utilize at most two airstream mechanisms.

In interjections, the other two mechanisms may be employed. For example, in countries as diverse as Sweden, Turkey, and Togo, a pulmonic ingressive ("gasped" or "inhaled") vowel is used for back-channeling or to express agreement, and in France a lingual egressive (a "spurt") is used to express dismissal. The only language where such sounds are known to be contrastive in normal vocabulary is the extinct ritual language Damin (also the only language outside Africa with clicks); however, Damin appears to have been intentionally designed to differ from normal speech.

Pulmonic initiation

Initiation by means of the lungs (actually the diaphragm and ribs) is called pulmonic initiation. The vast majority of sounds used in human languages are pulmonic egressives. In most languages, including all the languages of Europe (excluding the Caucasus), all phonemes are pulmonic egressives.

The only attested use of a phonemic pulmonic ingressive is a lateral fricative in Damin, a ritual language formerly used by speakers of Lardil in Australia. This can be written with the extended version of the International Phonetic Alphabet as [ɬ↓]. !Xóõ has ingression as a phonetic detail in one series of its clicks, which are ingressive voiceless nasals with delayed aspiration, [↓ŋ̊ʘʰ ↓ŋ̊ǀʰ ↓ŋ̊ǁʰ ↓ŋ̊!ʰ ↓ŋ̊ǂʰ]. Peter Ladefoged considers these to be among the most difficult sounds in the world. Other languages, for example in Taiwan, have been claimed to have pulmonic ingressives, but these claims have either proven to be spurious or to be occasional phonetic detail.

In interjections, but not in normal words, pulmonic ingressive vowels or words occur on all continents.[6] This is commonly done for back-channeling (as with [ə↓] in Ewe) or affirmation (as with [ɸʷ↓] in Swedish). In English, an audible intake of breath, [hːː↓], or an indrawn consonant such as [tʰ↓] or [p͡t↓] is used in a conversation to indicate that someone is about to speak or is preparing to continue speaking.[7] In some languages, such as Finnish and Amharic, entire phrases may be uttered with an ingressive airstream. (See ingressive sound.)

Glottalic initiation

It is possible to initiate airflow in the upper vocal tract by means of the vocal cords or glottis. This is known as glottalic initiation.

For egressive glottalic initiation, one lowers the glottis (as if to sing a low note), closes it as for a glottal stop, and then raises it, building up pressure in the oral cavity and upper trachea. Glottalic egressives are called ejectives. The glottis must be fully closed to form glottalic egressives, or the air column would flow backwards over it; it is therefore impossible to pronounce voiced ejectives. Ejective allophones of voiceless stops occur in many varieties of English at the ends of intonation units.[8]

For ingressive glottalic initiation, the sequence of actions performed in glottalic pressure initiation is reversed:  one raises the glottis (as if to sing a high note), closes it, and then lowers it to create suction in the upper trachea and oral cavity. Glottalic ingressives are called implosives, although they may involve zero airflow rather than actual inflow. Because the air column would flow forwards over the descending glottis, it is not necessary to fully close it, and implosives may be voiced; indeed, voiceless implosives are exceedingly rare.

It is usual for implosives to be voiced. Instead of keeping the glottis tightly closed, it is tensed but left slightly open to allow a thin stream of air through. Unlike pulmonic voiced sounds, in which a stream of air passes through a usually-fixed glottis, in voiced implosives a mobile glottis passes over a nearly motionless air column to cause vibration of the vocal cords. Phonations that are more open than modal voice, such as breathy voice, are not conducive to glottalic sounds because in these the glottis is held relatively open, allowing air to readily flow through and preventing a significant pressure difference from building up behind the articulator.

Because the oral cavity is so much smaller than the lungs, vowels and approximants cannot be pronounced with glottalic initiation. So-called glottalized vowels and other sonorants use the more common pulmonic egressive airstream mechanism.

There is no clear divide between pulmonic and glottalic sounds. Some languages may have consonants which are intermediate. For example, glottalized consonants in London English, such as the t in rat [ˈɹæʔt], may be weakly ejective. Similarly, fully voiced stops in languages such as Thai, Zulu, and Maidu are weakly implosive. This ambiguity does not occur with the next airstream mechanism, lingual, which is clearly distinct from pulmonic sounds.[9]

Lingual (velaric) initiation

This section needs additional citations for verification. Please help improve this article by adding citations to reliable sources in this section. Unsourced material may be challenged and removed. (July 2020) (Learn how and when to remove this template message)

The third form of initiation in human language is lingual or velaric initiation, where a sound is produced by a closure at two places of articulation, and the airstream is formed by movement of the body of the tongue. Lingual stops are more commonly known as clicks, and are almost universally ingressive. The word lingual is derived from Latin lingua, which means tongue.

To produce a lingual ingressive airstream, first close the vocal tract at two places: at the back of the tongue, as in a velar or uvular stop, and simultaneously with the front of the tongue or the lips, as in a coronal or bilabial stop. These holds may be voiceless, voiced, or nasalized. Then lower the body of the tongue to rarefy the air above it. The closure at the front of the tongue is opened first, as the click "release"; then the closure at the back is released for the pulmonic or glottalic click "accompaniment" or "efflux". This may be aspirated, affricated, or even ejective. Even when not ejective, it is not uncommon for the glottis to be closed as well, for a triply articulated consonant, and this third closure is released last to produce a glottalized click. Clicks are found in very few languages, notably the Khoisan languages of southern Africa and some nearby tongues such as Zulu. They are more often found in extra-linguistic contexts, such as the "tsk tsk" sound many Westerners use to express regret or pity (a dental click), or the clucking noise used by many equestrians to urge on their horses (a lateral click).

Lingual egressive initiation is performed by reversing the sequence of a lingual ingressive: the front and back of the tongue (or lips and back of the tongue) seal off the vocal cavity, and the cheeks and middle of the tongue move inward and upward to increase oral pressure. The only attested use of a lingual egressive is a bilabial nasal egressive click in Damin. Transcribing this also requires the use of the Extended IPA, [ŋʘ↑].

Since the air pocket used to initiate lingual consonants is so small, it is not thought to be possible to produce lingual fricatives,[citation needed] vowels, or other sounds which require continuous airflow.

Clicks may be voiced, but they are more easily nasalized. This may be because the vocal cavity behind the rearmost closure, behind which the air passing through the glottis for voicing must be contained, is so small that clicks cannot be voiced for long. Allowing the airstream to pass through the nose enables a longer production.

Nasal clicks involve a combination of lingual and pulmonic mechanisms. The velum is lowered so as to direct pulmonic airflow through the nasal cavity during the lingual initiation. This nasal airflow may itself be egressive or ingressive, independently of the lingual initiation of the click. Nasal clicks may be voiced, but are very commonly unvoiced and even aspirated, which is rare for purely pulmonic nasals.

Airstream contours

This section needs additional citations for verification. Please help improve this article by adding citations to reliable sources in this section. Unsourced material may be challenged and removed. (July 2020) (Learn how and when to remove this template message)

In some treatments, complex clicks are posited to have airstream contours, in which the airstream changes between the front (click) and rear (non-click) release. There are two attested types: Linguo-pulmonic consonants, where the rear release is a uvular obstruent such as [q] or [χ]; and linguo-glottalic consonants, where the rear release is an ejective such as [qʼ] or [qχʼ].

Not only are simultaneous (rather than contour) implosive clicks possible, e.g. velar [ɠ͡ǂ] and uvular [ʛ͡ǂ], but velar implosive clicks are easier to produce than modally voiced clicks. However, they are not attested in any language.[10]

Percussive consonants

This section needs additional citations for verification. Please help improve this article by adding citations to reliable sources in this section. Unsourced material may be challenged and removed. (July 2020) (Learn how and when to remove this template message)

Consonants may be pronounced without any airstream mechanism. These are percussive consonants, where the sound is generated by one organ striking another. Percussive consonants are not phonemic in any known language, though the extensions to the IPA for disordered speech provide symbols for a bilabial percussive [ʬ] (smacking lips) and a bidental percussive [ʭ] (gnashing teeth). The only percussive known to be used in nondisordered speech is a sublingual percussive [¡] (a tongue slap) that appears allophonically in the release of alveolar clicks in the Sandawe language of Tanzania.[11]

Percussive consonants
Bilabial Bidental Sublingual
ʬ ʭ ¡

See also


  1. ^ Van Gilse PHG. (1948). Another Method of Speech Without Larynx. Acta Oto-Laryngologica, 36, Supplement 78, 109 – 110. doi:10.3109/00016484809122642
  2. ^ Diedrich WM. Youngstrom KA. (1966). Alaryngeal Speech. Springfield, Ill.: Thomas OCLC 347249
  3. ^ Weinberg B, Westerhouse J. (1973). A study of pharyngeal speech. J Speech Hear Disord. 38(1):111-8. PMID 4698378
  4. ^ a b Pike, Kenneth (1943). Phonetics. Michigan. pp. 103–5.
  5. ^ Ian Maddieson (2008) "Presence of Uncommon Consonants". In: Martin Haspelmath & Matthew S. Dryer & David Gil & Bernard Comrie (eds.) The World Atlas of Language Structures Online. Munich: Max Planck Digital Library, chapter 19. Available online at Accessed on 18 January 2011
  6. ^ Robert Eklund
  7. ^ Ogden (2009) An Introduction to English Phonetics, p. 9, 164.
  8. ^ Ogden p. 164
  9. ^ Ladefoged, Peter; Maddieson, Ian (1996). The Sounds of the World's Languages. Oxford: Blackwell. p. 78. ISBN 0-631-19815-6.
  10. ^ Kenneth Pike, ed. Ruth Brend (1972) Selected Writings: To Commemorate the 60th Birthday of Kenneth Lee Pike. p. 226
  11. ^ Wright, Richard, Ian Maddieson, Peter Ladefoged, Bonny Sands (1995). "A phonetic study of Sandawe clicks", UCLA Working Papers in Phonetics, No. 91: Fieldwork Studies in Targeted Languages III.