Article Instance

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

{
    "pk": 49929,
    "title": "Latent speech representations learned through self-supervised learning predict listeners' generalization of adaptation across talkers",
    "subtitle": null,
    "abstract": "Unfamiliar accents can pose a challenge to speech recognition. However, listeners often adapt quickly to novel accents, and even generalize this adaptation across talkers with the same accent. We investigate how such cross-talker generalization---critical to effective speech perception---is achieved. We take advantage of advances in automatic speech recognition to test whether comparatively simple similarity-based inferences can explain cross-talker generalization in human listeners. We use the latent perceptual space learned by the HuBERT model---shaped by the statistics of the speech signal and the objective to recognize speech---to meaningfully measure the similarity between talkers' pronunciation. We find that word-level similarity in this latent space predict listeners' ability to successfully generalize across talkers. We discuss consequences for theories of adaptive speech perception. In particular, our results explain why cross-talker variability is not a prerequisite for cross-talker generalization (contrary to influential accounts).",
    "language": "eng",
    "license": {
        "name": "",
        "short_name": "",
        "text": null,
        "url": ""
    },
    "keywords": [
        {
            "word": "Language understanding; Speech recognition; Computational Modeling"
        }
    ],
    "section": "Papers with Poster Presentation",
    "is_remote": true,
    "remote_url": "https://escholarship.org/uc/item/465543dw",
    "frozenauthors": [
        {
            "first_name": "Zhengyang",
            "middle_name": "",
            "last_name": "Jin",
            "name_suffix": "",
            "institution": "University of Sussex",
            "department": ""
        },
        {
            "first_name": "Yuhao",
            "middle_name": "",
            "last_name": "Zhu",
            "name_suffix": "",
            "institution": "University of Rochester",
            "department": ""
        },
        {
            "first_name": "T. Florian",
            "middle_name": "",
            "last_name": "Jaeger",
            "name_suffix": "",
            "institution": "University of Rochester",
            "department": ""
        }
    ],
    "date_submitted": null,
    "date_accepted": null,
    "date_published": "2025-01-02T00:00:00+06:00",
    "render_galley": null,
    "galleys": [
        {
            "label": "PDF",
            "type": "pdf",
            "path": "https://journalpub.escholarship.org/cognitivesciencesociety/article/49929/galley/37891/download/"
        }
    ]
}