Paper ID | SPE-45.3 | ||
Paper Title | TRANSFORMER BASED UNSUPERVISED PRE-TRAINING FOR ACOUSTIC REPRESENTATION LEARNING | ||
Authors | Ruixiong Zhang, Haiwei Wu, Wubo Li, Dongwei Jiang, Wei Zou, Xiangang Li, Didi Chuxing, China | ||
Session | SPE-45: Speech Analysis | ||
Location | Gather.Town | ||
Session Time: | Thursday, 10 June, 16:30 - 17:15 | ||
Presentation Time: | Thursday, 10 June, 16:30 - 17:15 | ||
Presentation | Poster | ||
Topic | Speech Processing: [SPE-ANLS] Speech Analysis | ||
IEEE Xplore Open Preview | Click here to view in IEEE Xplore | ||
Abstract | Recently, a variety of acoustic tasks and related applications arised. For many acoustic tasks, the labeled data size may be limited. To handle this problem, we propose an unsupervised pre-training method using Transformer based encoder to learn a general and robust high-level representation for all acoustic tasks. Experiments have been conducted on three kinds of acoustic tasks: speech emotion recognition, sound event detection and speech translation. All the experiments have shown that pre-training using its own training data can significantly improve the performance. With a larger pre-training data combining MuST-C, Librispeech and ESC-US datasets, for speech emotion recognition, the UAR can further improve absolutely 4.3% on IEMOCAP dataset. For sound event detection, the F1 score can further improve absolutely 1.5% on DCASE2018 task5 development set and 2.1% on evaluation set. For speech translation, the BLEU score can further improve relatively 12.2% on En-De dataset and 8.4% on En-Fr dataset. |