High-quality Speech Coding with Sample RNN

We provide a speech coding scheme employing a generative model based on SampleRNN that, while operating at significantly lower bitrates, matches or surpasses the perceptual quality of state-of-the-art classic wide-band codecs. Moreover, it is demonstrated that the proposed scheme can provide a meaningful rate-distortion trade-off without retraining. We evaluate the proposed scheme in a series of listening tests and discuss limitations of the approach.

[1]  Turaj Zakizadeh Shabestary,et al.  Vector quantization by companding a union of Z-lattices , 2005, IEEE Transactions on Information Theory.

[2]  Antonio Bonafonte,et al.  Spanish Statistical Parametric Speech Synthesis Using a Neural Vocoder , 2018, INTERSPEECH.

[3]  Heiga Zen,et al.  WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[4]  Fredrik Nordén,et al.  Entropy constrained quantization of LSP parameters , 2003, INTERSPEECH.

[5]  Cong Zhou,et al.  Voice Conversion with Conditional SampleRNN , 2018, INTERSPEECH.

[6]  Kuldip K. Paliwal,et al.  Efficient vector quantization of LPC parameters at 24 bits/frame , 1993, IEEE Trans. Speech Audio Process..

[7]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[8]  Anssi Rämö,et al.  Voice quality evaluation of recent open source codecs , 2010, INTERSPEECH.

[9]  Roch Lefebvre,et al.  The adaptive multirate wideband speech codec (AMR-WB) , 2002, IEEE Trans. Speech Audio Process..

[10]  Thomas Eriksson,et al.  Improving predictive vector quantizers in speech coding applications , 1996 .

[11]  Jing Peng,et al.  An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network Trajectories , 1990, Neural Computation.

[12]  Xi Chen,et al.  PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications , 2017, ICLR.

[13]  Koen Vos,et al.  SILK Speech Codec , 2010 .

[14]  Yoshua Bengio,et al.  Char2Wav: End-to-End Speech Synthesis , 2017, ICLR.

[15]  Adam Coates,et al.  Deep Voice: Real-time Neural Text-to-Speech , 2017, ICML.

[16]  Quan Wang,et al.  Wavenet Based Low Rate Speech Coding , 2017, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[17]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[18]  Geoffrey E. Hinton,et al.  Training Recurrent Neural Networks , 2013 .

[19]  Yoshua Bengio,et al.  SampleRNN: An Unconditional End-to-End Neural Audio Generation Model , 2016, ICLR.

[20]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[21]  Cassia Valentini-Botinhao,et al.  Noisy speech database for training speech enhancement algorithms and TTS models , 2017 .

[22]  Heiga Zen,et al.  Parallel WaveNet: Fast High-Fidelity Speech Synthesis , 2017, ICML.

[23]  Zhen-Hua Ling,et al.  Samplernn-Based Neural Vocoder for Statistical Parametric Speech Synthesis , 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[24]  P. Hedelin.  A sinusoidal LPC vocoder , 2000, 2000 IEEE Workshop on Speech Coding. Proceedings. Meeting the Challenges of the New Millennium (Cat. No.00EX421).