Transcribed datasets typically contain speaker identity for each instance in the data. We investigate two ways to incorporate this information during training: Multi-Task Learning and Adversarial Learning. In multi-task learning, the goal is speaker prediction; we expect a performance improvement with this joint training if the two tasks of speech recognition and speaker recognition share a common set of underlying features. In contrast, adversarial learning is a means to learn representations invariant to the speaker. We then expect better performance if this learnt invariance helps generalizing to new speakers. While the two approaches seem natural in the context of speech recognition, they are incompatible because they correspond to opposite gradients back-propagated to the model. In order to better understand the effect of these approaches in terms of error rates, we compare both strategies in controlled settings. Moreover, we explore the use of additional un-transcribed data in a semi-supervised, adversarial learning manner to improve error rates. Our results show that deep models trained on big datasets already develop invariant representations to speakers without any auxiliary loss. When considering adversarial learning and multi-task learning, the impact on the acoustic model seems minor. However, models trained in a semi-supervised manner can improve error-rates.
|Title of host publication
|2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
|Institute of Electrical and Electronics Engineers Inc.
|Number of pages
|Published - May 2019
|44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12 May 2019 → 17 May 2019
|ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
|44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
|12/05/19 → 17/05/19
Bibliographical notePublisher Copyright:
© 2019 IEEE.
- adversarial learning
- automatic speech recognition
- multi-task learning
- neural networks