arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1412.1602cs.NEcs.LGstat.ML
收藏

基于注意递归NN的端到端连续语音识别:初步结果

End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results

University of Wrocław(弗罗茨瓦夫大学);Jacobs University Bremen(不来梅雅各布大学);Université de Montréal(蒙特利尔大学)

Jan Chorowski, Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio

摘要:

我们取代隐马尔可夫模型(HMM),这是传统上用于连续语音识别与一个双向递归神经网络编码器耦合到一个递归神经网络解码器,直接发出的音素流。使用注意力机制来建立输入和输出序列之间的对齐:解码器基于用由注意力机制选择的输入符号的子集创建的上下文来发射每个符号。我们报告的初步结果表明,这种新的方法实现音素出错率,相当于最先进的HMM为基础的解码器,TIMIT数据集。

英文摘要:

We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of phonemes. The alignment between the input and output sequences is established using an attention mechanism: the decoder emits each symbol based on a context created with a subset of input symbols elected by the attention mechanism. We report initial results demonstrating that this new approach achieves phoneme error rates that are comparable to the state-of-the-art HMM-based decoders, on the TIMIT dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑