Word-level Embeddings For Cross-task Transfer Learning In Speech Processing
2019 · Pierre Beckmann, Mikolaj Kegler, Milos Cernak
Abstract
Recent breakthroughs in deep learning often rely on representation learning and knowledge transfer. In recent years, unsupervised and self-supervised techniques for learning speech representation were developed to foster automatic speech recognition. Up to date, most of these approaches are task-specific and designed for within-task transfer learning between different datasets or setups of a particular task. In turn, learning task-independent representation of speech and cross-task applications of transfer learning remain less common. Here, we introduce an encoder capturing word-level representations of speech for cross-task transfer learning. We demonstrate the application of the pre-trained encoder in four distinct speech and audio processing tasks: (i) speech enhancement, (ii) language identification, (iii) speech, noise, and music classification, and (iv) speaker identification. In each task, we compare the performance of our cross-task transfer learning approach to task-specific b
Authors
(none)
Tags
Stats
Related papers
- Learning Problem-agnostic Speech Representations From Multiple Self-supervised Tasks (2019)15.54
- On The Transferability Of Whisper-based Representations For "in-the-wild" Cross-task Downstream Speech Applications (2023)0.00
- Towards Learning A Universal Non-semantic Representation Of Speech (2020)14.43
- Progressive Neural Networks For Transfer Learning In Emotion Recognition (2017)14.19
- Self-supervised Rewiring Of Pre-trained Speech Encoders: Towards Faster Fine-tuning With Less Labels In Speech Processing (2022)3.58
- Pretrained Semantic Speech Embeddings For End-to-end Spoken Language Understanding Via Cross-modal Teacher-student Learning (2020)9.92
- Supervised Acoustic Embeddings And Their Transferability Across Languages (2023)0.00
- Multi-task Voice Activated Framework Using Self-supervised Learning (2021)6.34