.png){kind=icon}
.png){kind=icon}
Return
Neurally Optimized Decoder for Low Bitrate Speech Codec
.png){kind=icon}
PRE
AI
DOI：10.1109/LSP.2021.3132557.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Recently, a conventional neural decoder for speech codec has shown promising performance. However, it typically requires some prior knowledge of decoding such as bit allocation or dequantization scheme, which is not a universal solution for many different kinds of speech codecs. In order to address this limitation, we propose a neurally optimized decoder based on a generative model which can directly reconstruct the speech from the bitstream without a prior knowledge. The proposed decoder mainly consists of two components: 1) a dequantization model to group and dequantize related bits from the bitstream and 2) a generative model to restore the speech conditioned on the output of the dequantization model. Through experiments with mixed excitation linear prediction (MELP), Advanced multi-band excitation (AMBE), and SPEEX at around 2.4 kb/s, it is showed that the proposed model showed better performance in most of the objective and subjective evaluation compared to the conventional speech codecs.
Keywords:
Decoding
Speech coding
Speech codecs
Bit rate
Encoding
Convolution
Knowledge engineering
Speech codecs
generative adversarial network
generative model
attention mechanism
Journal
IF:
9.6
Papers:
1.1W
Citations:
1.7W