Translate Reverberated Speech to Anechoic Ones: Speech Dereverberation with BERT
This work addresses speech dereverberation for audio processing applications, but it is incremental as it adapts an existing NLP model to a known task.
The paper tackled the problem of single-channel speech dereverberation by adapting the BERT model from NLP, using a pre-sequence network and pre-trained neural vocoder, and achieved performance comparable to state-of-the-art BLSTM-based models on the 3rd CHiME challenge data.
Single channel speech dereverberation is considered in this work. Inspired by the recent success of Bidirectional Encoder Representations from Transformers (BERT) model in the domain of Natural Language Processing (NLP), we investigate its applicability as backbone sequence model to enhance reverberated speech signal. We present a variation of the basic BERT model: a pre-sequence network, which extracts local spectral-temporal information and/or provides order information, before the backbone sequence model. In addition, we use pre-trained neural vocoder for implicit phase reconstruction. To evaluate our method, we used the data from the 3rd CHiME challenge, and compare our results with other methods. Experiments show that the proposed method outperforms traditional method WPE, and achieve comparable performance with state-of-the-art BLSTM-based sequence models.