Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems
Leveraging Unpaired Text Data for Training End-To-End Speech-to-Intent Systems
复制标题
利用不成对的文本数据训练端到端语音到意图系统
DOI:
--
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
M. Picheny
中科院分区:
文献类型:
--
作者:
Yinghui Huang;H. Kuo;Samuel Thomas;Zvi Kons;Kartik Audhkhasi;Brian Kingsbury;R. Hoory;M. Picheny
Training an end-to-end (E2E) neural network speech-to-intent (S2I) system that directly extracts intents from speech requires large amounts of intent-labeled speech data, which is time consuming and expensive to collect. Initializing the S2I model with an ASR model trained on copious speech data can alleviate data sparsity. In this paper, we attempt to leverage NLU text resources. We implemented a CTC-based S2I system that matches the performance of a state-of-the-art, traditional cascaded SLU system. We performed controlled experiments with varying amounts of speech and text training data. When only a tenth of the original data is available, intent classification accuracy degrades by 7.6% absolute. Assuming we have additional text-to-intent data (without speech) available, we investigated two techniques to improve the S2I system: (1) transfer learning, in which acoustic embeddings for intent classification are tied to fine-tuned BERT text embeddings; and (2) data augmentation, in which the text-to-intent data is converted into speech-to-intent data using a multi-speaker text-to-speech system. The proposed approaches recover 80% of performance lost due to using limited intent-labeled speech.