In this work, we propose Exformer, a time-domain architecture for target speaker extraction.
In real life, room effect, also known as room reverberation, and the present background noise degrade the quality of speech.
Singing voice separation aims to separate music into vocals and accompaniment components.
Neural vocoders have recently demonstrated high quality speech synthesis, but typically require a high computational complexity.
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so.
The presence of multiple talkers in the surrounding environment poses a difficult challenge for real-time speech communication systems considering the constraints on network size and complexity.
Given a limited set of labeled data, we present a method to leverage a large volume of unlabeled data to improve the model's performance.
Audio codecs based on discretized neural autoencoders have recently been developed and shown to provide significantly higher compression levels for comparable quality speech output.
We describe a novel approach for generating music using a self-correcting, non-chronological, autoregressive model.
Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is encountered in training data.
Many neural speech enhancement and source separation systems operate in the time-frequency domain.
Supervised deep learning has gained significant attention for speech enhancement recently.
Ranked #2 on Speech Enhancement on CHiME-3
We present enhancements to a speech-to-speech translation pipeline in order to perform automatic dubbing.