AI

Resource-constrained Stereo Singing Voice Cancellation

1 Mins read

We study the problem of stereo singing voice cancellation, a subtask of music source separation, whose goal is to estimate an instrumental background from a stereo mix. We explore how to achieve performance similar to large state-of-the-art source separation networks starting from a small, efficient model for real-time speech separation. Such a model is useful when memory and compute are limited and singing voice processing has to run with limited look-ahead. In practice, this is realised by adapting an existing mono model to handle stereo input. Improvements in quality are obtained by tuning model parameters and expanding the training set. Moreover, we highlight the benefits a stereo model brings by introducing a new metric which detects attenuation inconsistencies between channels. Our approach is evaluated using objective offline metrics and a large-scale MUSHRA trial, confirming the effectiveness of our techniques in stringent listening tests.


Source link

Related posts
AI

Microsoft Introduces Multilingual E5 Text Embedding: A Step Towards Multilingual Processing Excellence

3 Mins read
The primary challenge in text embeddings in Natural Language Processing (NLP) lies in developing models that can perform equally well across different…
AI

Researchers from UT Austin and AWS AI Introduce a Novel AI Framework 'ViGoR' that Utilizes Fine-Grained Reward Modeling to Significantly Enhance the Visual Grounding of LVLMs over Pre-Trained Baselines

2 Mins read
Integrating natural language understanding with image perception has led to the development of large vision language models (LVLMs), which showcase remarkable reasoning…
AI

CREMA by UNC-Chapel Hill: A Modular AI Framework for Efficient Multimodal Video Reasoning

2 Mins read
In artificial intelligence, integrating multimodal inputs for video reasoning stands as a frontier, challenging yet ripe with potential. Researchers increasingly focus on…

 

 

Leave a Reply

Your email address will not be published. Required fields are marked *