SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2409.07841 · 2024

TSELM: Target Speaker Extraction using Discrete Tokens and Language Models

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose TSELM, a novel target speaker extraction network that leverages discrete tokens and language models. TSELM utilizes multiple discretized layers from WavLM as input tokens and incorporates cross-attention mechanisms to integrate target speaker information. Language models are employed to capture the sequence dependencies, while a scalable HiFi-GAN is used to reconstruct the audio from the tokens. By applying a cross-entropy loss, TSELM models the probability distribution of output tokens, thus converting the complex regression problem of audio generation into a classification task. Experimental results show that TSELM achieves excellent results in speech quality and comparable results in speech intelligibility.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2409.07841")
get_code_for_paper("2409.07841")
have("2409.07841")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2409.07841.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2409.07841.svg)](https://syntology.ai/paper/2409.07841)

Connect an agent — have() is free.