Compartir
Speech Improvement via Transfer Learning (en Inglés)
Sameer Khurana
(Autor)
·
Tredition Gmbh
· Tapa Blanda
Speech Improvement via Transfer Learning (en Inglés) - Khurana, Sameer
$ 51.796
$ 64.745
Ahorras: $ 12.949
Elige la lista en la que quieres agregar tu producto o crea una nueva lista
✓ Producto agregado correctamente a la lista de deseos.
Ir a Mis Listas
Origen: Estados Unidos
(Costos de importación incluídos en el precio)
Se enviará desde nuestra bodega entre el
Lunes 22 de Julio y el
Miércoles 31 de Julio.
Lo recibirás en cualquier lugar de Argentina entre 1 y 3 días hábiles luego del envío.
Reseña del libro "Speech Improvement via Transfer Learning (en Inglés)"
This book develops transfer learning paradigms for spoken language processing applications.In particular, we tackle domain adaptation in the context of Automatic Speech Recognition (ASR) and Cross-Lingual Learning in Automatic Speech Translation (AST). The first part of the book develops an algorithm for unsupervised domain adaptation of End-to-End ASR models. In recent years, ASR performance has improved dramatically owing to the availability of large annotated corpora and novel neural network architectures. However, the ASR performance drops considerably when the training data distribution does not match the distribution that the model encounters during deployment (target domain). A straightforward remedy is collecting labeled data in the target domain and re-training the source domain ASR model. However, it is often expensive to collect labeled examples, while unlabeled data is more accessible. Hence, there is a need for unsupervised domain adaptation methods. To that end, we develop a simple but effective adaptation algorithm called the Dropout Uncertainty-Driven Self-Training (DUST). DUST repurposes the classic Self-Training (ST) algorithm to make it suitable for the domain adaptation problem.
- 0% (0)
- 0% (0)
- 0% (0)
- 0% (0)
- 0% (0)
Todos los libros de nuestro catálogo son Originales.
El libro está escrito en Inglés.
La encuadernación de esta edición es Tapa Blanda.
✓ Producto agregado correctamente al carro, Ir a Pagar.
