The child directed speech of twelve English-speaking mothers was analyzed in terms of utterance-level constructions. First, the mothers’ utterances were categorized in terms of general constructional categories such as Wh-questions, copulas and transitives. Second, mothers’ utterances within these categories were further specified in terms of the initial words that framed the utterance, item-ba...

A statistical model for segmentation and word discovery in child directed speech is presented. An incremental unsupervised learning algorithm to infer word boundaries based on this model is described and results of empirical tests showing that the algorithm is competitive with other models that have been used for similar tasks are also presented.

This paper presents a novel model that learns and exploits embeddings of phone ngrams for word segmentation in child language acquisition. Embedding-based models are evaluated on a phonemically transcribed corpus of child-directed speech, in comparison with their symbolic counterparts using the common learning framework and features. Results show that learning embeddings significantly improves ...

Repetitions in child-directed speech (CDS) have been shown to vary over time, and are suggested to affect first language acquisition. Correlations between verbal contents of repetitions in CDS and children’s language development have been suggested. The verbal contents of repetitions in Swedish CDS have not yet been investigated. The aim of this study was to examine the verbal contents of repet...

To learn the meanings of words, children must connect referents in the world around them with the sounds they hear. One proposed mechanism for this process is cross-situational word learning: tracking associations between words and objects across time. We consider the problem of anaphora for a crosssituational word learner: after an object has been introduced it is unlikely to be named in every...

This paper describes how distinctive features that classify speech sounds emerge from statistical analysis of Russian child-directed speech. The analysis is based on transcriptional representation of individual speech sounds. From the analysis of bigram distribution major natural classes such as consonants and vowels further subdivided into non-palatalized versus palatalized consonants and fron...

In this paper we focus on the use of acoustic as well as voice quality parameters to mark word stress in German. Our aim was to identify the speech parameters parents use to indicate word stress differences to their children. Therefore, mothers and their children were recorded during a period of at least one year while they performed a special playing task using word pairs that differ only in t...

A number of semantic space models from the cognitive science literature were compared by training on a corpus of child-directed speech and evaluating on three increasingly rigorous semantic tasks. The performance of families of models varied with the type of semantic data, and not all models were reasonably successful on each task, suggesting a narrowing of the space of plausible model architec...

Forced alignment would enable phonetic analyses of child directed speech (CDS) corpora which have existing transcriptions. But existing alignment systems are inaccurate due to the atypical phonetics of CDS. We adapt a Kaldi forced alignment system to CDS by extending the dictionary and providing it with heuristically-derived hints for vowel locations. Using this system, we present a new time-al...

Do statistical regularities between pronouns and verbs help children learn verb meanings? This question is addressed by an analysis of child directed speech. The results show that there are statistical regularities in the co-occurrences of pronouns and verbs that could be used to cue verbs that describe physical motion, psychological states, and features such as transitivity. The learnability o...