Phonological vocoding using artificial neural networks

By Milos Cernak, Blaise Potard, Philip N. Garner. 2015

23 citations recorded by the source corpus.

We investigate a vocoder based on artificial neural networks using a phonological speech representation. Speech decomposition is based on the phonological encoders, realised as neural network classifiers, that are trained for a particular language. The speech reconstruction process involves using a Deep Neural Network (DNN) to map phonological features posteriors to speech parameters - line spectra and glottal signal parameters - followed by LPC resynthesis. This DNN is trained on a target voice without transcriptions, in a semi-supervised manner. Both encoder and decoder are based on neural networks and thus the vocoding is achieved using a simple fast forward pass. An experiment with French vocoding and a target male voice trained on 21 hour long audio book is presented. An application of the phonological vocoder to low bit rate speech coding is shown, where transmitted phonological posteriors are pruned and quantized. The vocoder with scalar quantization operates at 1 kbps, with potential for lower bit-rate.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Srihari Kankanahalli
2. Philip N. Garner
3. Alexandros Lazaridis
4. Afsaneh Asaei
5. Milos Cernak

In Computer Vision and Pattern Recognition

1. Srihari Kankanahalli
2. Philip N. Garner
3. Alexandros Lazaridis
4. Afsaneh Asaei
5. Milos Cernak

In Signal Processing

1. Srihari Kankanahalli
2. Philip N. Garner
3. Alexandros Lazaridis
4. Afsaneh Asaei
5. Milos Cernak

Citations in the corpus

• End-To-End Optimized Speech Coding with Deep Neural Networks (2017, methodology): “[6] used a deep neural network as a phonological vocoder.”
• Composition of Deep and Spiking Neural Networks for Very Low Bit Rate Speech Coding (2016, methodology): “Three different NNs, shown in grey, are used: (i) phonological analysis DNNs [46] with 1-bit quantization encoding the binary segmental code, (ii) a spiking NN with stylisation encoding continuous F0, and (iii) a synthesis DNN [46] that decodes the segmental code to the speech parameters.”