paper-with-me

Papers

TSELM: Target Speaker Extraction using Discrete Tokens and Language Models

2024-09-12 · 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.

📄 PDF Abstract BibTeX arXiv:2409.07841

Code (1)

Beilong-Tang/TSELM 공식 구현 pytorch

Tasks

Audio GenerationTarget Speaker Extraction

Methods 이 논문이 사용한 방법론

HiFi-GAN HiFi-GAN is a generative adversarial network for speech synthesis. HiFi-GAN consists of one generator and two discriminators: multi-scale and multi-period discriminators. The…

Similar Papers 제목 키워드 기반

Discl-VC: Disentangled Discrete Tokens and In-Context Learning for Controllable Zero-Shot Voice Conversion

2025-05-30 · Kaidi Wang, Wenhao Guan, Ziyue Jiang, Hukai Huang 외

Currently, zero-shot voice conversion systems are capable of synthesizing the voice of unseen speakers. However, most existing approaches struggle to accurately replicate the speaking style of the source speaker or mimic…

In-Context LearningVoice Conversion

Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction

2025-06-02 · Wang Dai, Archontis Politis, Tuomas Virtanen

We propose a novel approach that utilizes inter-speaker relative cues to distinguish target speakers and extract their voices from mixtures. Continuous cues (e.g., temporal order, age, pitch level) are grouped by relativ…

AttributeSpeech Extraction

Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization

2026-07-05 · Ryota Komatsu, Kota Kawakita, Takuma Okamoto, Takahiro Shinozaki hf

Unsupervised syllabic tokenization aims to learn discrete syllabic tokens that capture latent linguistic content-related structure from raw speech. Recent syllabic tokenization methods employ teacher-student distillation…

Boundary Detection

High Fidelity Text-to-Speech Via Discrete Tokens Using Token Transducer and Group Masked Language Model

2024-06-25 · Joun Yeop Lee, Myeonghun Jeong, Minchan Kim, Ji-Hyun Lee 외

We propose a novel two-stage text-to-speech (TTS) framework with two types of discrete tokens, i.e., semantic and acoustic tokens, for high-fidelity speech synthesis. It features two core components: the Interpreting mod…

Computational EfficiencyLanguage ModelingLanguage ModellingSpeech Synthesis+2

LauraTSE: Target Speaker Extraction using Auto-Regressive Decoder-Only Language Models

2025-04-10 · Beilong Tang, Bang Zeng, Ming Li

We propose LauraTSE, an Auto-Regressive Decoder-Only Language Model for Target Speaker Extraction (TSE) based on the LauraGPT backbone. It employs a small-scale auto-regressive decoder-only language model which takes the…

DecoderLanguage ModelingLanguage ModellingTarget Speaker Extraction