Handling Background Noise in Neural Speech Generation

02/23/2021

∙

Recent advances in neural-network based generative modeling of speech has shown great potential for speech coding. However, the performance of such models drops when the input is not clean speech, e.g., in the presence of background noise, preventing its use in practical applications. In this paper we examine the reason and discuss methods to overcome this issue. Placing a denoising preprocessing stage when extracting features and target clean speech during training is shown to be the best performing strategy.

READ FULL TEXT

Handling Background Noise in Neural Speech Generation

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

Improving RNN Transducer With Target Speaker Extraction and Neural Uncertainty Estimation

Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

Parametric Resynthesis with neural vocoders

An Evaluation of Three-Stage Voice Conversion Framework for Noisy and Reverberant Conditions

Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect

Handling Background Noise in Neural Speech Generation

Related Research

A Teacher-student Framework for Unsupervised Speech Enhancement Using Noise Remixing Training and Two-stage Inference

Improving RNN Transducer With Target Speaker Extraction and Neural Uncertainty Estimation

Controllable Multichannel Speech Dereverberation based on Deep Neural Networks

Parametric Resynthesis with neural vocoders

An Evaluation of Three-Stage Voice Conversion Framework for Noisy and Reverberant Conditions

Enhancing into the codec: Noise Robust Speech Coding with Vector-Quantized Autoencoders

A Benchmarking on Cloud based Speech-To-Text Services for French Speech and Background Noise Effect