Robust Speech Recognition Based on Dereverberation Parameter Optimization Using Acoustic Model Likelihood
スポンサーリンク
概要
- 論文の詳細を見る
Automatic speech recognition (ASR) in reverberant environments is a challenging task. Most dereverberation techniques address this problem through signal processing and enhances the reverberant waveform independent from the speech recognizer. In this paper, we propose a novel scheme to perform dereverberation in relation with the likelihood of the back-end ASR system. Our proposed approach effectively selects the dereverberation parameters, in the form of multiband scale factors, so that they improve the likelihood of the acoustic model. Then, the acoustic model is retrained using the optimal parameters. During the recognition phase, we implement additional optimization of the parameters. By using Gaussian mixture model (GMM), the process for selecting the scale factors become efficient. Moreover, we remove the dependency of the adopted dereverberation technique on the room impulse response (RIR) measurement, by using an artificial RIR generator and selecting based on the acoustic likelihood. Experimental results show significant improvement in recognition performance with the proposed method over the conventional approach.
論文 | ランダム
- 歯科医療従事者の心理的ストレスを軽減させるための個性心理學による分類応用からの検証(第1報)
- 電気検知システムを用いた袋状二重シートの健全性評価技術の開発
- A社テレワーク試行実験の実証分析 : テレワーカーを取り巻く環境と実施頻度の関係に着目して
- New correction algorithms for multiple comparisons in case-control multilocus association studies based on haplotypes and diplotype configurations
- 電気検知方式を用いた二重遮水シートの損傷孔規模の把握