Файл:Connectionist Temporal Classification - Labelling Unsegmented Sequence Data with Recurrent Neural Networks.pdf

Материал из Материалы по машинному обучению
Перейти к: навигация, поиск
Connectionist_Temporal_Classification_-_Labelling_Unsegmented_Sequence_Data_with_Recurrent_Neural_Networks.pdf(0 × 0 пикселей, размер файла: 261 КБ, MIME-тип: application/pdf)

Alex Graves1 alex@idsia.ch Santiago Fern´andez1 santiago@idsia.ch Faustino Gomez1 tino@idsia.ch Ju¨rgen Schmidhuber1,2 juergen@idsia.ch 1 Istituto Dalle Molle di Studi sull’Intelligenza Artificiale (IDSIA), Galleria 2, 6928 Manno-Lugano, Switzerland 2 Technische Universit¨at Mu¨nchen (TUM), Boltzmannstr. 3, 85748 Garching, Munich, Germany


Many real-world sequence learning tasks require the prediction of sequences of labels from noisy, unsegmented input data. In speech recognition, for example, an acoustic signal is transcribed into words or sub-word units. Recurrent neural networks (RNNs) are powerful sequence learners that would seem well suited to such tasks. However, because they require pre-segmented training data, and post-processing to transform their outputs into label sequences, their applicability has sofarbeenlimited. This paperpresents a novel method for training RNNs to label unsegmented sequences directly, thereby solving both problems. An experiment on the TIMIT speech corpus demonstrates its advantages over both a baseline HMM and a hybrid HMM-RNN.

Keywords: Hidden Markov Model (HMM; Rabiner, 1989), hybrid HMM-RNN, Connectionist temporal classification network (CTC), temporal classification (Kadous, 2002)

История файла

Нажмите на дату/время, чтобы просмотреть, как тогда выглядел файл.

текущий17:05, 22 декабря 20160 × 0 (261 КБ)Slikos (обсуждение | вклад)
  • Вы не можете перезаписать этот файл.

Следующая 1 страница ссылается на данный файл: