The most thorough treatment of the Kiowa sound system is by Laurel Watkins in a generative framework. A consideration of prosodic phenomena with acoustic analysis is in Sivertsen (1956). Earlier discussions of phonemics are Trager (1960), Merrifield (1959), Wonderly et al. (1954), and Harrington (1928).
The 23 consonants of Kiowa:
Bilabial | Dental | Alveolar | Palatal | Velar | Glottal | ||
---|---|---|---|---|---|---|---|
Nasal | m | n | |||||
Stop | voiced | b | d | ɡ | |||
voiceless | p | t | ts | k | ʔ | ||
aspirated | pʰ | tʰ | kʰ | ||||
ejective | pʼ | tʼ | tsʼ | kʼ | |||
Fricative | voiced | z | |||||
voiceless | s | ç | h | ||||
Approximant | (w) | l | j |
In the orthography (used here) of the native Kiowa speaker, Parker McKenzie, who collaborated with both J.P. Harrington and Laurel Watkins, these are represented as below (parenthetic letters are used only at the end of the syllable):
Bilabial | Dental | Alveolar | Palatal | Velar | Glottal | ||
---|---|---|---|---|---|---|---|
Nasal | m | n | |||||
Stop | voiced | b | d | g | |||
voiceless | f (p) | j (t) | ch | c (k) | (t) | ||
aspirated | p | t | k | ||||
ejective | v | th | x | q | |||
Fricative | voiced | z | |||||
voiceless | s | sy | h | ||||
Approximant | w | l | y |
Kiowa has six contrasting vowel qualities with three heights and a front-back distinction. Additionally, there is an oral-nasal contrast on all six vowels. For example, nasality is the only difference between ā́u /ʔɔ́ː/ ('to gamble') and ā́u /ʔɔ̃́ː/ ('to give').
The oral-nasal contrast, however, is neutralized in the environment of nasal consonants, where only nasalized vowels occur. Watkins phonemicizes an oral vowel in these contexts: mā́ /máː/ ('up') is phonetically [mã́ː], máun /mɔ́n/ ('probably') is phonetically [mɔ̃́n].
Kiowa vowels have an underlying two-way length contrast (short vs. long). However, a number of phonological issues restrict the length contrast. (See the syllable and phonotactics for details.)
Kiowa has three tones: high, low, falling. No minimal triple is available, but the distinctions can be illustrated pairwise: à ~ á (agreement prefixes for 1sg and 3pl unaccusatives), ḕ ('when') ~ ḗ ('here'); àl ('also)' ~ âl ('chase' perfective imperative), chḕ ('when') ~ chê ('horse'); cául ('cattle')~ câul ('some'), gṹ('wise') ~ gû ('hit'). Note that length is not indicated on vowels with falling tone in the current orthography: this is because falling tone is generally only realized over long vowels or a vowel plus resonant (/j/, /l/, /m/, or /n/). However, there are at least two words with falling tone realized before /t/, both of them minimally contrastive with high tone: bót ('guts') ~ bôt ('because'), chát ('door') ~ chât ('cheque'). This behaviour contrasts with /p/; suffixation of /p/ to verbs with falling tone causes the vowel to shorten and become simply high, as in root ~ perfective pairs gû ~ góp ('hit'), kî ~ tép ('exit'). One speaker has been recorded with the pronunciation [êtʼ] ('big') in contrast to other speakers' [ét] (the compounding form, êl, as in êlmā̀ 'old woman', has falling tone).
The falling tone has glottalized realizations (creaky voice, tense voice, with glottal stop) in some contexts.
There are also a number of tone sandhi effects.
Surface syllables in Kiowa must consist of a vowel nucleus. Syllable onsets are optional and can consist of single consonant or a consonant followed by a palatal glide [j]. A single vowel may be followed by an optional syllable coda consonant or the vowel may optionally be long. Thus, the following syllables are found in Kiowa: V, CV, CjV, VC, CVC, CjVC, Vː, CVː, CjVː. This can be succinctly represented as the syllable equation below.
A number of phonotactic restrictions are found limiting the possible combinations of sounds. These are discussed below.
Onset. All consonants can occurs as a single consonant onset. However, /l/ only occurs word-initially in loan words (e.g., láyàn 'lion', Láut 'Lawton').
Nucleus. The syllable nucleus can be any vowel, which can be either short or long.
Coda. The coda position may be filled only by /p, t, m, n, l, j/. Palatal /j/ only follows the vowels /u, o, ɔ, a/ (i.e. the palatal may not occur after non-low front vowels).[5]