Towards Learning a Universal Non-Semantic Representation of Speech
| Autor: | Ira Shavitt, Dotan Emanuel, Aren Jansen, Marco Tagliasacchi, Ronnie Maor, Joel Shor, Yinnon Haviv, Oran Lang, Felix de Chaumont Quitry, Omry Tuval |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer Science - Machine Learning Computer science Machine Learning (stat.ML) 02 engineering and technology 010501 environmental sciences Machine learning computer.software_genre 01 natural sciences Computer Science - Sound Machine Learning (cs.LG) Domain (software engineering) Personalization Audio and Speech Processing (eess.AS) Statistics - Machine Learning 020204 information systems FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering Code (cryptography) Representation (mathematics) 0105 earth and related environmental sciences business.industry Variety (linguistics) Benchmark (computing) Embedding Artificial intelligence business Transfer of learning computer Electrical Engineering and Systems Science - Audio and Speech Processing |
| Zdroj: | INTERSPEECH |
| Popis: | The ultimate goal of transfer learning is to reduce labeled data requirements by exploiting a pre-existing embedding model trained for different datasets or tasks. The visual and language communities have established benchmarks to compare embeddings, but the speech community has yet to do so. This paper proposes a benchmark for comparing speech representations on non-semantic tasks, and proposes a representation based on an unsupervised triplet-loss objective. The proposed representation outperforms other representations on the benchmark, and even exceeds state-of-the-art performance on a number of transfer learning tasks. The embedding is trained on a publicly available dataset, and it is tested on a variety of low-resource downstream tasks, including personalization tasks and medical domain. The benchmark, models, and evaluation code are publicly released. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|