LanSER：语言模型支持的语音情感识别
LanSER: Language-Model Supported Speech Emotion Recognition
AI总结：
提出LanSER方法，利用预训练大型语言模型通过弱监督学习推断弱情感标签，在大型无标签数据集上预训练的模型微调后优于基线模型并提升标签效率。
摘要：
语音情感识别（SER）模型通常依赖昂贵的人工标注数据进行训练，这使得将方法扩展到大型语音数据集和细粒度情感分类法变得困难。我们提出了LanSER，这是一种通过弱监督学习利用预训练大型语言模型推断弱情感标签，从而能够使用无标签数据的方法。为了推断受限于分类法的弱标签，我们采用文本蕴含方法，利用自动语音识别提取语音转录文本，并选择具有最高蕴含分数的情感标签。实验结果表明，使用这种弱监督在大型数据集上预训练的模型，在微调后优于标准SER数据集上的其他基线模型，并展现出更高的标签效率。尽管仅在源自文本的标签上进行预训练，我们表明所得表征似乎能够对语音的韵律内容进行建模。
英文摘要：
Speech emotion recognition (SER) models typically rely on costly human-labeled data for training, making scaling methods to large speech datasets and nuanced emotion taxonomies difficult. We present LanSER, a method that enables the use of unlabeled data by inferring weak emotion labels via pre-trained large language models through weakly-supervised learning. For inferring weak labels constrained to a taxonomy, we use a textual entailment approach that selects an emotion label with the highest entailment score for a speech transcript extracted via automatic speech recognition. Our experimental results show that models pre-trained on large datasets with this weak supervision outperform other baseline models on standard SER datasets when fine-tuned, and show improved label efficiency. Despite being pre-trained on labels derived only from text, we show that the resulting representations appear to model the prosodic content of speech.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
