Translate Reverberated Speech to Anechoic Ones: Speech Dereverberation with BERT
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification
Acoustic modeling for Overlapping Speech Recognition: JHU Chime-5 Challenge System
RVAE-EM: Generative speech dereverberation based on recurrent variational auto-encoder and convolutive transfer function
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation
Speech Enhancement and Dereverberation with Diffusion-based Generative Models
MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes
토론
이 논문과 연결된 포럼 글이 아직 없습니다.