南非呼叫中心音频多风格培训
Multi-style Training for South African Call Centre Audio
摘要:
失配数据是自动语音识别(ASR)系统面临的一个挑战性问题。用于解决不匹配数据的最常见技术之一是多样式训练(MTR),这是一种数据增强的形式,其尝试将训练数据转换为更能代表测试数据;并学习适用于不同条件的鲁棒表示。如果测试条件未知,则此任务可能非常具有挑战性。我们探讨了在深度神经网络隐马尔可夫模型(DNN-HMM)ASR系统的背景下,当测试条件与训练条件不同时,不同MTR风格对系统性能的影响。使用LibriSpeech语料库创建了一个受控环境,在那里我们隔离了不同MTR风格对最终系统性能的影响。我们评估我们的研究结果,南非呼叫中心数据集,包含嘈杂的,WAV 49编码的音频。
英文摘要:
Mismatched data is a challenging problem for automatic speech recognition (ASR) systems. One of the most common techniques used to address mismatched data is multi-style training (MTR), a form of data augmentation that attempts to transform the training data to be more representative of the testing data; and to learn robust representations applicable to different conditions. This task can be very challenging if the test conditions are unknown. We explore the impact of different MTR styles on system performance when testing conditions are different from training conditions in the context of deep neural network hidden Markov model (DNN-HMM) ASR systems. A controlled environment is created using the LibriSpeech corpus, where we isolate the effect of different MTR styles on final system performance. We evaluate our findings on a South African call centre dataset that contains noisy, WAV49-encoded audio.
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。