论文标题
飞跃提交到Chime-6 ASR挑战}
LEAP Submission to CHiME-6 ASR Challenge}
论文作者
论文摘要
本文报告了Chime-6挑战的飞跃提交。 Chime-6自动语音识别（ASR）挑战轨道1涉及在具有多方相互作用的家庭环境中嘈杂和回响的声学条件中的语音识别。对于挑战提交，LEAP系统使用了广泛的数据增强和分解的时间延迟神经网络（TDNN）体系结构。我们还探索了一种神经结构，该神经结构与LSTM层交织在一起。就相对单词误差的改进而言，提交的系统将Kaldi配方提高了2％。
This paper reports the LEAP submission to the CHiME-6 challenge. The CHiME-6 Automatic Speech Recognition (ASR) challenge Track 1 involved the recognition of speech in noisy and reverberant acoustic conditions in home environments with multiple-party interactions. For the challenge submission, the LEAP system used extensive data augmentation and a factorized time-delay neural network (TDNN) architecture. We also explored a neural architecture that interleaved the TDNN layers with LSTM layers. The submitted system improved the Kaldi recipe by 2% in terms of relative word-error-rate improvements.
