arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.08497eess.AScs.CLcs.SD
收藏

基于注意力的在线语音识别传感器

Attention-based Transducer for Online Speech Recognition

LAIX Inc.(LAIX公司)

Bin Wang, Yan Yin, Hui Lin

摘要:

最近的研究揭示了递归神经网络转换器(RNN-T)用于端到端(E2 E)语音识别的潜力。在一些最流行的E2 E系统中,包括RNN-T,注意力编码器-解码器(AED)和连接主义时间分类(CTC),RNN-T具有一些明显的优势,因为它支持流识别并且没有帧独立性假设。尽管RNN-T研究取得了重大进展,但在训练速度和准确性方面仍面临性能挑战。我们提出了基于注意力的传感器与修改RNN-T在两个方面。首先,我们在联合网络中引入块式注意。其次,在编码器中引入自注意。我们提出的模型在训练速度和准确性方面都优于RNN-T。对于训练,我们实现了超过1.7倍的加速。使用500小时的LAIX非母语英语训练数据,基于注意力的传感器比基线RNN-T产生约10.6%的WER降低。使用超过10,000小时的完整数据进行训练,我们的最终系统比使用最佳Kaldi TDNN-f配方训练的系统减少了约5.5%的WER。在不降低WER的情况下进行8位权重量化后,在生产服务器的单个CPU核心上,RTF和延迟分别下降到0.34~0.36和268~409毫秒。

英文摘要:

Recent studies reveal the potential of recurrent neural network transducer (RNN-T) for end-to-end (E2E) speech recognition. Among some most popular E2E systems including RNN-T, Attention Encoder-Decoder (AED), and Connectionist Temporal Classification (CTC), RNN-T has some clear advantages given that it supports streaming recognition and does not have frame-independency assumption. Although significant progresses have been made for RNN-T research, it is still facing performance challenges in terms of training speed and accuracy. We propose attention-based transducer with modification over RNN-T in two aspects. First, we introduce chunk-wise attention in the joint network. Second, self-attention is introduced in the encoder. Our proposed model outperforms RNN-T for both training speed and accuracy. For training, we achieves over 1.7x speedup. With 500 hours LAIX non-native English training data, attention-based transducer yields ~10.6% WER reduction over baseline RNN-T. Trained with full set of over 10K hours data, our final system achieves ~5.5% WER reduction over that trained with the best Kaldi TDNN-f recipe. After 8-bit weight quantization without WER degradation, RTF and latency drop to 0.34~0.36 and 268~409 milliseconds respectively on a single CPU core of a production server.

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。

↑