Article Instance

HTTP 200 OK
Allow: GET
Content-Type: application/json
Vary: Accept

{
    "pk": 24474,
    "title": "Multimodal Input Aids a Bayesian Model of Phonetic Learning",
    "subtitle": null,
    "abstract": "One of the many tasks facing the typically-developing child language learner is learning to discriminate between distinctive sounds that make up words in their native language. We investigate whether multimodal information---specifically adult speech coupled with video frames of speakers' faces---benefits a computational model of phonetic learning. We introduce a method for creating high-quality synthetic videos of speakers' faces for an existing audio corpus. Our learning model, when trained and tested on audiovisual inputs, achieves 8.1% relative improvement on a phoneme discrimination battery compared to a model trained and tested on audio-only input. It outperforms the audio model by 3.9% when tested on audio-only data, suggesting that visual information facilitates the acquisition of acoustic distinctions. In noisy audio environments, our audiovisual model recovers 67% of the loss in performance of the audio model relative to non-noisy environments. These results demonstrate that visual information benefits an ideal learner and illustrate multiple ways that children might leverage visual cues when learning to discriminate speech sounds.",
    "language": "eng",
    "license": {
        "name": "",
        "short_name": "",
        "text": null,
        "url": ""
    },
    "keywords": [
        {
            "word": "Computer Science; Linguistics; Psychology; Face Processing; Language learning; Phonology; Computational Modeling"
        }
    ],
    "section": "Papers with Poster Presentation",
    "is_remote": true,
    "remote_url": "https://escholarship.org/uc/item/4n21p3k2",
    "frozenauthors": [
        {
            "first_name": "Sophia",
            "middle_name": "",
            "last_name": "Zhi",
            "name_suffix": "",
            "institution": "Massachusetts Institute of Technology",
            "department": ""
        },
        {
            "first_name": "Roger",
            "middle_name": "",
            "last_name": "Levy",
            "name_suffix": "",
            "institution": "Massachusetts Institute of Technology",
            "department": ""
        },
        {
            "first_name": "Stephan",
            "middle_name": "C.",
            "last_name": "Meylan",
            "name_suffix": "",
            "institution": "MIT",
            "department": ""
        }
    ],
    "date_submitted": null,
    "date_accepted": null,
    "date_published": "2024-01-01T18:00:00Z",
    "render_galley": {
        "label": "PDF",
        "type": "pdf",
        "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/24474/galley/21390/download/"
    },
    "galleys": [
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/24474/galley/14071/download/"
        },
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/24474/galley/21390/download/"
        }
    ]
}