ASR Performance Prediction on Unseen Broadcast Programs using Convolutional Neural Networks
2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2018)
摘要
In this paper, we address a relatively new task: prediction of ASR performance on unseen broadcast programs. We first propose an heterogenous French corpus dedicated to this task. Two prediction approaches are compared: a state-of-the-art performance prediction based on regression (engineered features) and a new strategy based on convolutional neural networks (learnt features). We particularly focus on the combination of both textual (ASR transcription) and signal inputs. While the joint use of textual and signal features did not work for the regression baseline, the combination of inputs for CNNs leads to the best WER prediction performance. We also show that our CNN prediction remarkably predicts the WER distribution on a collection of speech recordings.
更多查看译文
关键词
Performance Prediction,Large Vocabulary Continuous Speech Recognition,Convolutional Neural Networks
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络