The written symbols that represent the sounds of spoken language in the Greek/Latin alphabets (i.e., consonants and vowels) can be traced back to the Phoenician script (an extinct Semitic language), in which only the consonants were represented in print. Nowadays, other Semitic languages like Hebrew or Arabic only employ consonantal information in writing, except for some long vowels. This may be taken to suggest that consonants may be more important than vowels during lexical access. Indeed, as a large number of experiments conducted in different languages have consistently found, skilled adult readers rely more on consonants than on vowels during visual-word recognition and reading [1]–[12].

New at al. [8] reported an elegant and conclusive demonstration of the advantage of consonantal over vocalic information at the early stages of visual-word recognition with skilled adult readers in French. Using a lexical decision task with briefly presented (50 ms) forwardly masked primes, the authors employed nonword primes that preserved either the consonants (e.g., duvo) or the vowels (e.g., rifa) of the target words (e.g., DIVA) – identical (e.g., diva-DIVA) and unrelated (e.g., rufo-DIVA) nonword primes were also introduced as controls. They found faster recognition times for words preceded by a consonant-preserving prime than for words preceded by a vowel-preserving prime (i.e., duvo-DIVA faster than rifa-DIVA), whereas word recognition times in the vowel-preserving condition were comparable to those observed in the unrelated priming condition (see also [5] for converging evidence using subset primes: csn-CASINO faster than aio-CASINO). New et al. [8] concluded that “lexical representations are accessed more reliably through consonantal than vocalic information” (p. 1226), and established the presence of a consonant bias at early stages of visual-word recognition in adult readers.

Despite the strong evidence of an advantage of consonants over vowels at early stages of visual-word recognition in skilled adult readers, little is known about how early in development the consonant bias emerges and evolves during reading acquisition. The experiments reported in this paper address this issue being, to the best of our knowledge, the first that aims to track the emergence of the consonant bias at the early stages of visual-word recognition in developing readers. Although there is no empirical evidence about the emergence of the consonant bias in reading acquisition, a substantial amount of research has explored how infants and children process consonants and vowels in speech. Nazzi [13] using a name-based categorization paradigm (in which children are taught two different labels for three name-object pairs - two of them sharing the same label [e.g., /pize/] and the third object has a different label [e.g., /tize/] – and then are asked to put together the objects that share the same label), was one of the first authors to show that 20-month-old children are able to distinguish between two labels of the name-object pairs that differ by one consonant (e.g., /pize/- /tize/), but failed to learn the name-object pairs that differ by one vowel (e.g., /pize/- /pyze/). The advantage of consonants over vowels in word learning was found to be independent of the type of consonants used (plosives [13]; fricatives, liquids, and nasals [14]) and of their position in the speech signal (onset: /pod/–/bod/; coda: /pod/–/pot/- [13], [15]). Other studies have provided similar evidence with younger- (14-month-olds [16]; 16-month-olds [17]; 17-month-olds [18]) and older-infants (30-month-olds [19]), and preschool children (3 to 5 year-olds [20]). Moreover, measuring the comprehension of correct and mispronounced instances of familiar words (e.g., /bal/) in toddlers, several studies [21]-[24] found that the recognition of mispronounced familiar words was more impaired after a consonant transformation (e.g., /bal/–/gal/) than after a vowel transformation (e.g., /bal/–/bul/) and this result seems to be independent of the position (onset vs. coda) the consonant change occurs in [25].

Taken together, the above-cited studies show that the consonant bias in speech emerges early in development. That is, infants rely more on consonants than on vowels when they have to code lexicalized forms and/or recognize familiar stimuli. One remaining question is whether the advantage of consonants over vowels observed early in speech would also be observed at early stages of reading acquisition, i.e., when children enter school and formally start to learn how to read. Reading is a very complex cognitive process that involves the ability to construct linguistic meaning from written representations of language. When children start reading they need to learn to map the written forms onto the existing spoken word representations to access word meanings and to “know” (at least in alphabetic languages) that changes in a single letter may imply the existence of different words in the lexicon (e.g., invern vs. infern). Children are very skillful in this process and progress very quickly from an initial stage of sublexical letter-by-letter phonological recoding to a whole-word orthographic recognition process (allowed by the development of a specialized system of parallel letter processing) which is thought to constitute the main pathway to access meaning from print in skilled readers [26]–[28]. Of particular interest here is the Consonant-Vowel hypothesis developed by Nespor et al. [29], which states that consonants are more informative for lexical distinctions in lexical access, whereas vowels are more informative for (morpho)syntactic processing. This functional dissociation, which has been supported by several studies - see, for example [30]–[33], was initially proposed to explain the difficulties that young children encounter when they have to simultaneously learn the lexical and syntactic properties of words. The rationale here is that dividing the labor of consonants/vowels at two linguistic levels would be less demanding for children and more effective in child language acquisition than using both consonants and vowels to learn the lexical and syntactic information at the same time [29]. Therefore, the presence of a consonant bias at early stages of reading acquisition in our study would provide additional support to the functional distinction between consonants and vowels in language processing, thus extending the results previously observed in speech with infants and children to young readers.

Furthermore, developmental evidence on the emergence of the consonant bias in reading acquisition may also help build and constraint future implementations of computational models of visual-word recognition. Although it is generally recognized that, at some point in processing, the recognition of a printed word is mediated by the consonant-vowel status of its letters (i.e., the graphemic/phonological Consonant/Vowel [CV] skeleton of words [1], [2], [34], [35], [36]), none of the current computational models of visual-word recognition and reading take the consonant-vowel status of letters into account in their ‘front-end’ and, instead, they assume that each letter in a word (whether consonant or vowel) is initially encoded in the same way (e.g., LTRS model [37]; overlap model [38]; spatial coding model [39]; Bayesian reader model [40]; SERIOL model [41]; overlap open-bigram model [42]; EZ-Reader model [43]; SWIFT model [44]). One potential limitation of all these models is their ‘static’ nature (i.e., they assume well-formed and unalterable set of parameters of visual-word recognition in a mature reading system), as they are not explicitly designed to deal with the dynamics of a developing reading system. Leaving aside the difficulty of creating a (formal) developmental model of visual-word recognition, it is critical to know what the important benchmarks are (i.e., what is there to simulate) and how they evolve in time (i.e., does the consonant bias appear at all levels of reading skill or only with skilled readers?). Clearly, developmental data on the consonant bias can contribute to a deeper understanding of the dynamics of language representation and processing while these abilities are still developing, thus helping to disentangle the mechanisms from which consonants and vowels are processed.

In the current series of experiments, we aimed to analyze the emergence of the consonant bias in reading. In particular, we examined the relative contribution of consonants and vowels at early stages of word recognition by conducting a series of experiments – using the procedure employed by New et al. [8] – with beginning (2^nd Graders) and intermediate (4^th Graders) European Portuguese (EP) developing readers. As a further control, we also conducted the parallel experiment with EP skilled adult readers (university students) - see [45]–[50] for a similar strategy. As in the New et al.'s experiment [8], we employed a masked priming paradigm and a highly common visual-word identification task (i.e., lexical decision). Di- and tri-syllabic target words (e.g., VASO [VASE] and PIRATA [PIRATE], respectively) selected from the children's lexical Portuguese database ESCOLEX (51) were preceded by a forwardly masked nonword prime (for 50 ms) which could be a consonant-preserving prime (e.g., vesu-VASO or pureto-PIRATA) or a vowel-preserving prime (e.g., zalo-VASO or gicala-PIRATA). We also included an identity priming condition (e.g., vaso-VASO or pirata-PIRATA) and an unrelated priming condition (e.g., tuce-VASO or bocelo-PIRATA) as further controls. As in the New et al. experiment, consonant and vowel position in words was controlled by using two distinct orthographic and phonological structures as defined by consonant (Cs) and vowel (Vs) order within the word in each syllable length. Thus, half of the target words started with a consonant (CVCV - e.g., VASO [VASE]; and CVCVCV words - e.g., PIRATA [PIRATE]) - hereafter CV words, and the other half started with a vowel (VCVC – e.g., AZUL [BLUE]; and VCVCVC words - e.g., ANIMAL [ANIMAL]) - hereafter VC words. We should note here that the consonant bias in the New et al. study (8) was observed both for CV (e.g., DIVA) and VC target words (e.g., OPUS). The only relevant difference with respect to the New et al. experiment was that here we employed the go/no-go variant of the lexical decision task (i.e., respond to words and refrain from responding to nonwords) rather than the yes/no variant. The go/no-go procedure was preferred because it provides faster and more accurate responses in young readers than the yes/no procedure, while tapping the same underlying processes [52], [53] - see also [54], for a mathematical model of the go/no-go task.

To sum up, Experiment 1 was conducted with EP adult skilled readers since previous experiments on consonant/vowel asymmetries were conducted in other languages (e.g., English, French, Spanish, etc.). To anticipate the findings, we found faster recognition times for target words preceded by consonantal information than for target words preceded by vocalic information (i.e., a consonant bias) regardless of the initial letter in the word (i.e., the magnitude of the consonant bias was similar for CV and VC words), hence replicating the New et al. [8] findings in EP. Thus, the critical question in this paper was whether the consonant bias would also be observed in beginning and intermediate developing readers. Experiment 2 was conducted with 2^nd Grade children and Experiment 3 with 4^th Grade children. If there is a developmental continuity between what is observed early in speech processing (at least in the acquisition of new words or in the recognition of familiar ones) and early in reading acquisition, one would expect an advantage of consonantal over vocalic information even at initial stages of reading acquisition.

Recent research with skilled adult readers has consistently revealed an advantage of consonants over vowels (i.e., a “consonant bias”) at early stages of visual-word recognition and reading [1]–[12]. The present masked-priming lexical decision experiments extend this line of research to developing readers (2^nd and 4^th graders) by examining the emergence of consonant/vowel asymmetry at early stages of visual-word recognition. The main findings can be summed up as follows: (i) an advantage of consonant-preserving primes over vowel-preserving primes was observed with college-aged readers in Portuguese, thus extending previous experiments with adult skilled readers in other alphabetic languages (e.g., English, French, Spanish) to Portuguese; (ii) an advantage of consonant-preserving primes over vowel-preserving primes occurred for 4^th graders but not for 2^nd graders (i.e., the consonant bias emerges at a later, intermediate stage of reading acquisition); and (iii) the advantage of consonant-preserving primes over vowel-preserving primes was observed for both CV and VC words in adult skilled readers, though restricted to CV words in 4^th graders (i.e., the consonant bias emerges gradually in reading acquisition being modulated by the CV word structure).

Contrary to what was observed in the vast number of studies conducted with young children and preschoolers in speech processing [13]–[25] and with adult skilled readers in visual-word recognition [1]–[12], the present masked priming experiments reveal that in early stages of reading acquisition (2^nd Grade children) neither consonant-preserving primes (e.g., pureto-PIRATA) nor vowel-preserving primes (e.g., gicala-PIRATA) had a significant effect upon the processing of the target words relative to an unrelated condition. At this stage, only identical primes facilitated the recognition of the target words. The absence of any significant effect of consonant- and vowel-preserving primes in beginning readers may well stem from the fact the child's orthographic processing system is coarsely tuned and has not had enough time to “learn” how to optimize the mapping of letter representation onto semantics using the best quality information in the stimulus [28], [47], [59]. The technique used in this experiment (i.e., masked priming) taps into rapid and automatic visual-word recognition processes, and the standard 50 ms duration of prime exposure was probably insufficient to cause a reliable effect on word recognition with partial primes. We must keep in mind that only half of the letters in the target word were preserved in the consonant-preserving primes (e.g., pureto-PIRATA) or in the vowel-preserving primes (e.g., gicala-PIRATA) and there is modeling evidence that shows that the quality of extraction information from word stimuli (i.e., “drift rate” in a diffusion model) is lower in young readers than in adults [62]. Prior demonstrations of masked form priming effects with beginning readers employed either a greater perceptual overlap between primes and targets - such as one-letter different primes and/or transposed-letter primes [28], [45], [47] or a longer time exposure of the prime (120 ms) [60]. Further research is necessary to examine in detail the interplay between prime duration and age/reading skills across different manipulations (e.g., identity primes, partial primes, and unrelated primes) with the masked priming paradigm.

Nevertheless, as age/reading skills increase, young readers process printed words more accurately and rapidly and the orthographic system is able to maximize the information provided by the stimulus in order recognize words. This would readily explain the emergence of the relative advantage of consonant-preserving primes over vowel-preserving primes in 4^th graders (around 9-10 year olds). Importantly, the advantage of consonants over vowels in visual word recognition at this stage of reading acquisition (intermediate) was observed for CV words (i.e., words like VASO [VASE] and PIRATA [PIRATE]), but not for VC words (i.e., words like AZUL [BLUE] and ANIMAL [ANIMAL]). Note that in this study, CV and VC target words were matched in lexical frequency, contextual diversity, and number of orthographic neighbors (see the Materials section). A possible explanation for this unexpected effect may rely on the overall familiarity with the CV skeletal structure of words. In Romance languages such as Portuguese, words with a CV structure are more frequent than words with a VC structure [63]. An a posteriori analysis of the distribution of the orthographic word structures in the G₁–G₄ level of the ESCOLEX children's database [51] supports this idea as it revealed that words with a CV structure occur in 82.5% of all four- and six-letter wordforms, whereas words with a VC structure occur only in 11.6% of all four- and six-letter wordforms. Moreover, words with a CV structure occur not only in more words in young readers' lexicons but also in words with a higher frequency of occurrence (the token frequency of CV words is 69,945.97 per million words, while the token frequency for VC is 8,280.66). Therefore, the lack of a priming effect observed in 4^th graders for VC words could be due to the fact that the sublexical activation generated from the prime was reduced when the word structure was less familiar. Importantly, as reading skills and exposure to printed words increase, this sensitivity to the word's orthographic structure at early stages of visual-word processing tends to vanish and the consonant bias extends to other less familiar word structures. Indeed, both VC and CV word structures produced a similar consonant bias in adult skilled-readers (see Experiment 1; see also [8]) which might signal that the orthographic system reached its maturity and is able to maximize the information provided in the stimulus that best helps to identify words.

Before considering the implications of the consonant bias for models of visual-word recognition in terms of an abstract CV skeleton in which consonants and vowels play different (functional) roles, it may be important to examine an alternative (more perceptual) explanation. It might be argued that consonants and vowels behave differently during lexical access because of the different characteristics in letter shape. While many consonant letters have an ascending (e.g., b, t, d, k, l) or descending (e.g., j, q, g, p) shape, all vowels are neutral letters (e.g., a, u, e). Therefore, the detection of an ascending/descending letter offers unambiguous cues of the consonant/status of the letter and it may help word processing. Although Grainger and Dufau [64] used this reasoning to explain why lowercase words are identified more rapidly than uppercase words [65], [66], it can be easily generalized to the processing of the lowercase stimuli in masked priming (i.e., the ascending/descending shape of the lowercase primes could have provided a head start). To minimize the role of the letter-shape information in the consonant bias phenomenon, we conducted a replication of Experiment 1 (40 Portuguese university students; M_age: 20.2 years; range: 18–29; 32 female) in which the primes were presented in uppercase and targets were presented in lowercase [67] for a comparison between lowercase/uppercase vs. uppercase/lowercase prime-target pairs). Keep in mind that uppercase stimuli do not have a specific letter shape, so that the letter-shape of the prime stimuli does not provide any clues on the consonant/vowel status of the letters [49]. Results revealed exactly the same pattern as in Experiment 1. In particular, we found a sizeable consonant bias effect (17 ms in the latency data [0.3% in the error data]; the parallel response time advantage in Experiment 1 was 19 ms). Therefore, the consonant bias that has been found in Experiment 1 (or in previous research) is not due to some uncontrolled effect of the ascending/neutral/descending nature of the letters in the lowercase primes. This finding is also consistent with previous evidence that has failed to find consistent effects of letter/word shape with normal readers [49], [68].

What are the implications of these findings for (developmental) computational models of visual word recognition? The presence of a robust consonant bias not only for adult readers, but also for young readers does suggest that some form of CV skeleton needs to be added to current computational models of visual-word recognition that do not encode the letters as consonants or vowels (e.g., LTRS model [37]; overlap model [38]; spatial coding model [39]; Bayesian reader model [40]; SERIOL model [41]; overlap open-bigram model [42]; EZ-Reader model [43]; SWIFT model [44]). Furthermore, we have shown that the consonant bias in developing readers is modulated by the familiarity of the words' structure (i.e., it emerges primarily in the canonical CV structure and is afterwards generalized to VC structures in adult skilled readers), thus suggesting that the study of the consonant bias in visual-word recognition should not be dissociated from the linguistic experience with printed words and with the statistical regularities of the language.

One remaining issue at the theoretical level here is at which level of processing the CV skeleton takes place, whether at a very early orthographic level or when phonology starts playing a role. Of particular interest here would be to explore the consonant bias in word structures in which there is a mismatch between the orthographic and the phonological mapping, as in cases of consonantal clusters (e.g., words like “strong”[strσŋ] a CCCVCC orthographic structure and a CCCVC phonological structure) and/or in vowel hiatus words from a developmental perspective (e.g., words like “chaos”[′keΙσs] a CCVVC orthographic structure and a CVVC phonological structure – as recently used with adult readers [36]). Clearly, further developmental research should explore to what extent the consonant bias is linked to the phonological (or lexical) characteristics of the word-processing system during visual-word recognition and reading by using techniques that tap the time course of processing such as ERP recording and/or eye movement paradigms.

To conclude, the present findings set some constraints on future (developmental) models of visual-word recognition that incorporate a Consonant/Vowel skeleton [1], [34], [35]. Firstly, consonantal information produces greater facilitation than vowel information (i.e., a “consonant bias”) at early stages of visual-word recognition with young readers, at least from 4th Grade onwards. Secondly, the emergence of the consonant bias is modulated by the familiarity of the CV skeleton structure – it occurs firstly with the most familiar CVCV/CVCVCV word structure. Further research is necessary to examine in greater detail the time course of consonantal vs. vocalic processing of young readers during sentence reading.