Papers › TSELM: Target Speaker Extraction using Discrete Tokens and Language Models

TSELM: Target Speaker Extraction using Discrete Tokens and Language Models

12 Sep 2024arXiv:2409.07841archive 2025-07-28

Beilong Tang, Bang Zeng, Ming Li

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.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

Beilong-Tang/TSELM officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio GenerationTarget Speaker Extraction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

HiFi-GAN

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections