TIGER Speech

--- pipeline_tag: audio-to-audio tags: - audio license: apache-2.0 language: - en --- <p align="center"> </p> <h3 align="center">TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation</h3> <p align="center"> <strong>Mohan Xu^*, Kai Li^*, Guo Chen, Xiaolin Hu</strong><br> <strong>Tsinghua University, Beijing, China</strong><br> <strong>^*Equal contribution</strong><br> <a href="https://arxiv.org/abs/2410.01469">📜 ICLR 2025</a> | <a href="https://cslikai.cn/TIGER/">🎶 Demo</a> | <a href="https://huggingface.co/datasets/JusperLee/EchoSet">🤗 Dataset</a> <p align="center"> <img src="https://visitor-badge.laobi.icu/badge?page_id=JusperLee.TIGER" alt="访客统计" /> <img src="https://img.shields.io/github/stars/JusperLee/TIGER?style=social" alt="GitHub stars" /> <img alt="Static Badge" src="https://img.shields.io/badge/license-Apache%202.0-blue.svg" /> </p> <p align="center"> > TIGER is a lightweight model for speech separation which effectively extracts key acoustic features through frequency band-split, multi-scale and full-frequency-frame modeling. ## 💥 News - **[2025-01-23]** We release the code and pre-trained model of TIGER! 🚀 - **[2025-01-23]** We release the TIGER model and the EchoSet dataset! 🚀 ## 📜 Abstract In this paper, we propose a speech separation model with significantly reduced parameter size and computational cost: Time-Frequency Interleaved Gain Extraction and Reconstruction Network (TIGER). TIGER leverages prior knowledge to divide frequency bands and applies compression on frequency information. We employ a multi-scale selective attention (MSA) module to extract contextual features, while introducing a full-frequency-frame attention (F^3A) module to capture both temporal and frequency contextual information. Additionally, to more realistically evaluate the performance of speech separation models in complex acoustic environments, we introduce a novel dataset called EchoSet. This dataset includes noise and more realistic reverberation (e.g., considering object occlusions and material properties), with speech from two speakers overlapping at random proportions. Experimental results demonstrated that TIGER significantly outperformed state-of-the-art (SOTA) model TF-GridNet on the EchoSet dataset in both inference speed and separation quality, while reduci...

Source context: 3485 downloads · 24 likes · Pipeline audio-to-audio · Repo JusperLee/TIGER-speech