paper-with-me

Papers

Conditional Diffusion Model for Target Speaker Extraction

2023-10-07 · Theodor Nguyen, Guangzhi Sun, Xianrui Zheng, Chao Zhang, Philip C Woodland

We propose DiffSpEx, a generative target speaker extraction method based on score-based generative modelling through stochastic differential equations. DiffSpEx deploys a continuous-time stochastic diffusion process in the complex short-time Fourier transform domain, starting from the target speaker source and converging to a Gaussian distribution centred on the mixture of sources. For the reverse-time process, a parametrised score function is conditioned on a target speaker embedding to extract the target speaker from the mixture of sources. We utilise ECAPA-TDNN target speaker embeddings and condition the score function alternately on the SDE time embedding and the target speaker embedding. The potential of DiffSpEx is demonstrated with the WSJ0-2mix dataset, achieving an SI-SDR of 12.9 dB and a NISQA score of 3.56. Moreover, we show that fine-tuning a pre-trained DiffSpEx model to a specific speaker further improves performance, enabling personalisation in target speaker extraction.

📄 PDF Abstract BibTeX arXiv:2310.04791

Code (0)

등록된 구현이 없습니다.

Tasks

modelTarget Speaker Extraction

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Target Speech Extraction with Conditional Diffusion Model

2023-08-08 · Naoyuki Kamo, Marc Delcroix, Tomohiro Nakatani

Diffusion model-based speech enhancement has received increased attention since it can generate very natural enhanced signals and generalizes well to unseen conditions. Diffusion models have been explored for several sub…

DenoisingmodelSpeech DenoisingSpeech Enhancement+1

AlphaFlowTSE: One-Step Generative Target Speaker Extraction via Conditional AlphaFlow

2026-03-11 · Duojia Li, Shuhan Zhang, Zihan Qian, Wenxuan Wu 외 arxiv

In target speaker extraction (TSE), we aim to recover target speech from a multi-talker mixture using a short enrollment utterance as reference. Recent studies on diffusion and flow-matching generators have improved targ…

Speech Recognition

Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Data

2022-05-30 · Sungwon Kim, Heeseung Kim, Sungroh Yoon

We propose Guided-TTS 2, a diffusion-based generative model for high-quality adaptive TTS using untranscribed data. Guided-TTS 2 combines a speaker-conditional diffusion model with a speaker-dependent phoneme classifier …

text-to-speechText to Speech

Spectron: Target Speaker Extraction using Conditional Transformer with Adversarial Refinement

2024-09-02 · Tathagata Bandyopadhyay

Recently, attention-based transformers have become a de facto standard in many deep learning applications including natural language processing, computer vision, signal processing, etc.. In this paper, we propose a trans…

Target Speaker Extraction

SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline

2025-05-25 · Helin Wang, Jiarui Hai, Dongchao Yang, Chen Chen 외

Target Speech Extraction (TSE) aims to isolate a target speaker's voice from a mixture of multiple speakers by leveraging speaker-specific cues, typically provided as auxiliary audio (a.k.a. cue audio). Although recent a…

Speech ExtractionSpeech Separation