AV Digits Database

AV Digits Database 是一个视听数据库，其中包含正常、耳语和无声语音。 53 名参与者从 3 种不同的视图（正面、45 和侧面）录制，以三种语音模式发音数字和短语。该数据库由两部分组成：数字和短语。在第一部分，参与者被要求以随机顺序阅读 0 到 9 的 10 个英文数字五次。如果是非英语母语的人，这部分也以参与者的母语重复。共有来自 16 个国家的 53 名参与者（41 名男性和 12 名女性）被记录，平均年龄和标准差分别为 26.7 和 4.3 岁。在第二部分，参与者被要求阅读 10 个短语。短语与 OuluVS2 数据库中使用的短语相同：“Excuse me”、“Goodbye”、“Hello”、“How are you”、“Nice to meet you”、“See you”、“I am sorry” 、“谢谢”、“玩得开心”、“不客气”。同样，每个短语以 3 种不同的模式重复五次，即中性、耳语和无声讲话。这部分记录了 39 名参与者（32 名男性和 7 名女性），平均年龄和标准差分别为 26.3 和 3.8 岁。

The AV Digits Database is an audiovisual database containing normal, whispered, and silent speech. Fifty-three participants were recorded from three different viewpoints (frontal, 45-degree, and profile) while articulating numbers and phrases in three speech modes. The database consists of two parts: digits and phrases. In the first part, participants were asked to read the 10 English digits from 0 to 9 five times in random order. For non-native English speakers, this part was also repeated in the participants' native languages. A total of 53 participants (41 males and 12 females) from 16 countries were recorded, with an average age of 26.7 years and a standard deviation of 4.3 years. In the second part, participants were asked to read 10 phrases. The phrases are identical to those used in the OuluVS2 database: "Excuse me", "Goodbye", "Hello", "How are you", "Nice to meet you", "See you", "I am sorry", "Thank you", "Have fun", "You're welcome". Similarly, each phrase was repeated five times in three different modes: neutral, whispered, and silent speech. Thirty-nine participants (32 males and 7 females) were recorded for this part, with an average age of 26.3 years and a standard deviation of 3.8 years.

搜集汇总

背景与挑战

背景概述

AV Digits Database是一个多语言、多视角的视听语音数据库，包含53名参与者在不同语音模式（正常、耳语、无声）下录制的数字和短语，适用于语音识别和视觉语音识别研究。