2017/12/01 by W. Bastiaan Kleijn, Kleijn, W. Bastiaan, Felicia S. C. Lim +11 · 3 citations
Computer Science · Engineering · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Music and Audio Processing #Signal Processing (eess.SP) #Sound (cs.SD) #Speech Recognition and Synthesis #Speech and Audio Processing #cs.SD #eess.AS #eess.SP #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1712.01120
5 pages, 2 figures
arxiv created 2017/12/01 · openalex publication_date 2017/12/01 · arxiv updated 2017/12/05 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04
Traditional parametric coding of speech facilitates low rate but provides poor reconstruction quality because of the inadequacy of the model used. We describe how a WaveNet generative speech model can be used to generate high quality speech from the bit stream of a standard parametric coder operating at 2.4 kb/s. We compare this parametric coder with a waveform coder based on the same generative model and show that approximating the signal waveform incurs a large rate penalty. Our experiments confirm the high performance of the WaveNet based coder and show that the speech produced by the system is able to additionally perform implicit bandwidth extension and does not significantly impair recognition of the original speaker for the human listener, even when that speaker has not been used during the training of the generative model.