Pre-training for feature extraction is an increasingly studied approach to get better continuous representations of audio and text content. In the present work, we use wav2vec and camemBERT as self-supervised learned models to represent our data in order to perform continuous emotion recognition from speech (SER) on AlloSat, a large French emotional database describing the satisfaction dimension, and on the state of the art corpus SEWA focusing on valence, arousal and liking dimensions. To the authors' knowledge, this paper presents the first study showing that the joint use of wav2vec and BERT-like pre-trained features is very relevant to deal with continuous SER task, usually characterized by a small amount of labeled training data. Evaluated by the well-known concordance correlation coefficient (CCC), our experiments show that we can reach a CCC value of 0.825 instead of 0.592 when using MFCC in conjunction with word2vec word embedding on the AlloSat dataset.

本文研究音频和文本的预训练提取特征方法，使用 wav2vec 和 camemBERT 模型进行连续情感识别任务，同时采用 SEWA 数据集，证明 wav2vec 和 BERT 预训练特征的联合使用在处理连续 SER 任务中表现非常合适。通过实验证明，新方法的 CCC 值达到 0.825，而传统的 MFCC 和 word2vec 仅为 0.592。

利用自监督预训练的声学和语言特征进行连续语音情感识别