Does anyone know if these results scale up to a large vocabulary? The better-than-human recognition results are really stunning, but a traditional problem with auto speech rec is sparsity in the training set, isn't it? Does anyone know if it will still work with 20,000 words in the vocabulary, and how much training is required to get there?
Slashdot Mirror
Does anyone know if these results scale up to a large vocabulary? The better-than-human recognition results are really stunning, but a traditional problem with auto speech rec is sparsity in the training set, isn't it? Does anyone know if it will still work with 20,000 words in the vocabulary, and how much training is required to get there?