Skip to content

请问我应该如何在保持低误唤醒率的情况下优化噪声场景下的唤醒率呢? #206

@Emma-Miao

Description

@Emma-Miao

尝试给模型训练集的正样本中增加「带噪声背景的唤醒词音频」,结果虽然「噪声场景下的唤醒率」提升了,但是误唤醒也提升了。请教一下,有没有更好的方式解决这个问题呢?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions