Does Infant-Directed Speech Help Phonetic Learning? A Machine Learning Investigation

Autor/inn/en	Ludusan, Bogdan; Mazuka, Reiko; Dupoux, Emmanuel
Titel	Does Infant-Directed Speech Help Phonetic Learning? A Machine Learning Investigation
Quelle	In: Cognitive Science, 45 (2021) 5, (31 Seiten) PDF als Volltext Verfügbarkeit
Zusatzinformation	ORCID (Ludusan, Bogdan)
Sprache	englisch
Dokumenttyp	gedruckt; online; Zeitschriftenaufsatz
ISSN	1551-6709
DOI	10.1111/cogs.12946
Schlagwörter	Infants; Child Language; Speech Communication; Phonetics; Articulation (Speech); Vowels; Acoustics; Foreign Countries; Japanese; Artificial Intelligence; Mathematics + Suchen Sie Ihr Suchwort? Infant; Toddler; Toddlers; Kleinkind; 'Children''s language'; Kindersprache; Phonetik; Fonetik; Akustik; Ausland; Japaner; Japanisch; Künstliche Intelligenz; Mathematik
Abstract	A prominent hypothesis holds that by speaking to infants in infant-directed speech (IDS) as opposed to adult-directed speech (ADS), parents help them learn phonetic categories. Specifically, two characteristics of IDS have been claimed to facilitate learning: "hyperarticulation," which makes the categories more "separable," and "variability," which makes the generalization more "robust." Here, we test the separability and robustness of vowel category learning on acoustic representations of speech uttered by Japanese adults in ADS, IDS (addressed to 18- to 24-month olds), or read speech (RS). Separability is determined by means of a distance measure computed between the five short vowel categories of Japanese, while robustness is assessed by testing the ability of six different machine learning algorithms trained to classify vowels to generalize on stimuli spoken by a novel speaker in ADS. Using two different speech representations, we find that hyperarticulated speech, in the case of RS, can yield better separability, and that increased between-speaker variability in ADS can yield, for some algorithms, more robust categories. However, these conclusions do not apply to IDS, which turned out to yield neither more separable nor more robust categories compared to ADS inputs. We discuss the usefulness of machine learning algorithms run on real data to test hypotheses about the functional role of IDS. (As Provided).
Anmerkungen	Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us
Erfasst von	ERIC (Education Resources Information Center), Washington, DC
Update	2024/1/01