We introduce CLaMP: Contrastive Language-Music Pre-training, which learns cross-modal representations between natural language and symbolic music using a music encoder and a text encoder trained jointly with a contrastive loss. To pre-train CLaMP, we collected a large dataset of 1.4 million music-text pairs. It employed text dropout as a data augmentation technique and bar patching to efficiently represent music data which reduces sequence length to less than 10\%. In addition, we developed a masked music model pre-training objective to enhance the music encoder's comprehension of musical context and structure. CLaMP integrates textual information to enable semantic search and zero-shot classification for symbolic music, surpassing the capabilities of previous models. To support the evaluation of semantic search and music classification, we publicly release WikiMusicText (WikiMT), a dataset of 1010 lead sheets in ABC notation, each accompanied by a title, artist, genre, and description. In comparison to state-of-the-art models that require fine-tuning, zero-shot CLaMP demonstrated comparable or superior performance on score-oriented datasets. Our models and code are available at https://github.com/microsoft/muzic/tree/main/clamp.

翻译：我们提出了CLaMP：对比语言-音乐预训练，该方法通过联合训练的对比损失函数，使音乐编码器和文本编码器学习自然语言与符号音乐之间的跨模态表示。为预训练CLaMP，我们收集了包含140万条音乐-文本对的大型数据集。该方法采用文本丢弃作为数据增强技术，并利用条形拼接高效表示音乐数据，将序列长度压缩至不足原始长度的10%。此外，我们设计了掩码音乐模型预训练目标，以增强音乐编码器对音乐语境和结构的理解能力。CLaMP集成文本信息，实现了符号音乐的语义搜索和零样本分类，性能超越此前模型。为支持语义搜索与音乐分类的评估，我们公开了WikiMusicText（WikiMT）数据集，包含1010份以ABC记谱法表示的领谱，每份标注有标题、艺术家、流派和描述信息。与需要微调的现有最优模型相比，零样本CLaMP在乐谱数据集上展现了相当甚至更优的性能。我们的模型与代码已开源至https://github.com/microsoft/muzic/tree/main/clamp。