We analyze the microstructure of child-adult interaction during naturalistic, daylong, automatically labeled audio recordings (13,836 hours total) of children (8- to 48-month-olds) with and without autism. We find that adult responses are more likely when child vocalizations are speech-related. In turn, a child vocalization is more likely to be speech-related if the previous speech-related child vocalization received an immediate adult response. Taken together, these results are consistent with the idea that there is a social feedback loop between child and caregiver that promotes speech-language development. Although this feedback loop applies in both typical development and autism, children with autism produce proportionally fewer speech-related vocalizations and the responses they receive are less contingent on whether their vocalizations are speech-related. We argue that such differences will diminish the strength of the social feedback loop with cascading effects on speech development over time. Differences related to socioeconomic status are also reported.

The INTERSPEECH 2017 Computational Paralinguistics Challenge addresses three different problems for the first time in research competition under well-defined conditions: In the Addressee sub-challenge, it has to be determined whether speech produced by an adult is directed towards another adult or towards a child; in the Cold sub-challenge, speech under cold has to be told apart from 'healthy' speech; and in the Snoring sub-challenge, four different types of snoring have to be classified. In this paper, we describe these sub-challenges, their conditions, and the baseline feature extraction and classifiers, which include data-learnt feature representations by end-to-end learning with convolutional and recurrent neural networks, and bag-of-audio-words for the first time in the challenge series.

We report on the emergence of functional flexibility in vocalizations of human infants. This vastly underappreciated capability becomes apparent when prelinguistic vocalizations express a full range of emotional content-positive, neutral, and negative. The data show that at least three types of infant vocalizations (squeals, vowel-like sounds, and growls) occur with this full range of expression by 3-4 mo of age. In contrast, infant cry and laughter, which are speciesspecific signals apparently homologous to vocal calls in other primates, show functional stability, with cry overwhelmingly expressing negative and laughter positive emotional states. Functional flexibility is a sine qua non in spoken language, because all words or sentences can be produced as expressions of varying emotional states and because learning conventional "meanings" requires the ability to produce sounds that are free of any predetermined function. Functional flexibility is a defining characteristic of language, and empirically it appears before syntax, word learning, and even earlier-developing features presumed to be critical to language (e.g., joint attention, syllable imitation, and canonical babbling). The appearance of functional flexibility early in the first year of human life is a critical step in the development of vocal language and may have been a critical step in the evolution of human language, preceding protosyntax and even primitive single words. Such flexible affect expression of vocalizations has not yet been reported for any nonhuman primate but if found to occur would suggest deep roots for functional flexibility of vocalization in our primate heritage.esearch on evolution and development of language has been devoted primarily to syntax, the uniquely human capacity to produce well-formed complex sentences (1-4). Additional work has targeted the emergence of simpler communicative structures and thus has shifted attention back in evolutionary time to an earlier possible split of hominins from the primate background. For example, research has considered the presumably earlier evolution of simple sentences or "protosyntax" (5). Other work influenced by recent trends in evolutionary developmental biology (evo-devo) (6, 7) has focused on infrastructure for language, invoking capabilities logically more foundational even than protosyntax and presumably moving the communicative differentiation of hominins from other primates much farther back. For example, symbolic expression in single words beginning in modern human development at about 12 mo is a precursor to even the simplest syntax (8). Moving the evolutionary focus even farther back in time, joint attention-infant pointing with gaze alternation between an object and an adult interactor, occurring before the end of the first year-is deemed a critical precursor to words (9). Similarly, canonical babbling (onset at about 7 mo) is a crucial step toward verbal vocabulary because development and imitation of canonical syllables (e.g., "baba") is required for extensive word lear...

A range of demographic variables influence how much speech young children hear. However, because studies have used vastly different sampling methods, quantitative comparison of interlocking demographic effects has been nearly impossible, across or within studies. We harnessed a unique collection of existing naturalistic, day-long recordings from 61 homes across four North American cities to examine language input as a function of age, gender, and maternal education. We analyzed adult speech heard by 3- to 20-month-olds who wore audio recorders for an entire day. We annotated speaker gender and speech register (child-directed or adult-directed) for 10,861 utterances from female and male adults in these recordings. Examining age, gender, and maternal education collectively in this ecologically-valid dataset, we find several key results. First, the speaker gender imbalance in the input is striking: children heard 2–3× more speech from females than males. Second, children in higher-maternal-education homes heard more child-directed speech than those in lower-maternal education homes. Finally, our analyses revealed a previously unreported effect: the proportion of child-directed speech in the input increases with age, due to a decrease in adult-directed speech with age. This large-scale analysis is an important step forward in collectively examining demographic variables that influence early development, made possible by pooled, comparable, day-long recordings of children’s language environments. The audio recordings, annotations, and annotation software are readily available for re-use and re-analysis by other researchers.

The INTERSPEECH 2019 Computational Paralinguistics Challenge addresses four different problems for the first time in a research competition under well-defined conditions: In the Styrian Dialects Sub-Challenge, three types of Austrian-German dialects have to be classified; in the Continuous Sleepiness Sub-Challenge, the sleepiness of a speaker has to be assessed as regression problem; in the Baby Sound Sub-Challenge, five types of infant sounds have to be classified; and in the Orca Activity Sub-Challenge, orca sounds have to be detected. We describe the Sub-Challenges and baseline feature extraction and classifiers, which include data-learnt (supervised) feature representations by the 'usual' ComParE and BoAW features, and deep unsupervised representation learning using the AUDEEP toolkit.