English
Related papers

Related papers: Training-Free Multi-Step Inference for Target Spea…

200 papers

Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…

Computation and Language · Computer Science 2026-04-09 Mauro Cettolo , Marco Gaido , Matteo Negri , Sara Papi , Luisa Bentivogli

In this paper we introduce a first attempt on understanding how a non-autoregressive factorised multi-speaker speech synthesis architecture exploits the information present in different speaker embedding sets. We analyse if jointly learning…

Audio and Speech Processing · Electrical Eng. & Systems 2023-07-20 Adriana Stan , Johannah O'Mahony

Extracting the desired speech from a mixture is a meaningful and challenging task. The end-to-end DNN-based methods, though attractive, face the problem of generalization. In this paper, we explore a sequential approach for target speech…

Audio and Speech Processing · Electrical Eng. & Systems 2020-11-02 Zhaoyi Gu , Lele Liao , Kai Chen , Jing Lu

Image retrieval using spoken language cues has emerged as a promising direction in multimodal perception, yet leveraging speech in multi-speaker scenarios remains challenging. We propose a novel Target Speaker Speech-Image Retrieval task…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-12 Wenhao Yang , Jianguo Wei , Wenhuan Lu , Xinyue Song , Xianghu Yue

The goal of this paper is to enhance Text-to-Audio generation at inference, focusing on generating realistic audio that precisely aligns with text prompts. Despite the rapid advancements, existing models often fail to achieve a reliable…

Audio and Speech Processing · Electrical Eng. & Systems 2025-09-25 Jaemin Jung , Jaehun Kim , Inkyu Shin , Joon Son Chung

Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…

Sound · Computer Science 2025-07-04 Wan Lin , Junhui Chen , Tianhao Wang , Zhenyu Zhou , Lantian Li , Dong Wang

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…

Audio and Speech Processing · Electrical Eng. & Systems 2023-10-10 Theodor Nguyen , Guangzhi Sun , Xianrui Zheng , Chao Zhang , Philip C Woodland

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

Speaker extraction algorithm relies on the speech sample from the target speaker as the reference point to focus its attention. Such a reference speech is typically pre-recorded. On the other hand, the temporal synchronization between…

Audio and Speech Processing · Electrical Eng. & Systems 2021-02-11 Zexu Pan , Ruijie Tao , Chenglin Xu , Haizhou Li

In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-17 Jisi Zhang , Catalin Zorila , Rama Doddipatla , Jon Barker

Universal sound separation (USS) aims to extract arbitrary types of sounds from real-world recordings. This can be achieved by language-queried target sound extraction (TSE), which typically consists of two components: a query network that…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-24 Hao Ma , Zhiyuan Peng , Xu Li , Mingjie Shao , Xixin Wu , Ju Liu

We propose a multichannel-to-multichannel target sound extraction (M2M-TSE) framework for separating multichannel target signals from a multichannel mixture of sound sources. Target sound extraction (TSE) isolates a specific target signal…

Audio and Speech Processing · Electrical Eng. & Systems 2024-09-20 Dayun Choi , Jung-Woo Choi

Target sound extraction consists of extracting the sound of a target acoustic event (AE) class from a mixture of AE sounds. It can be realized using a neural network that extracts the target sound conditioned on a 1-hot vector that…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-15 Marc Delcroix , Jorge Bennasar Vázquez , Tsubasa Ochiai , Keisuke Kinoshita , Shoko Araki

Recent advancements in speech synthesis have enabled large language model (LLM)-based systems to perform zero-shot generation with controllable content, timbre, speaker identity, and emotion through input prompts. As a result, these models…

Dominant researches adopt supervised training for speaker extraction, while the scarcity of ideally clean corpus and channel mismatch problem are rarely considered. To this end, we propose speaker-aware mixture of mixtures training (SAMoM),…

Audio and Speech Processing · Electrical Eng. & Systems 2022-04-18 Zifeng Zhao , Rongzhi Gu , Dongchao Yang , Jinchuan Tian , Yuexian Zou

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance…

Sound · Computer Science 2021-10-05 Yi Ma , Kong Aik Lee , Ville Hautamaki , Haizhou Li

The perceptual quality of neural text-to-speech (TTS) is highly dependent on the choice of the model during training. Selecting the model using a training-objective metric such as the least mean squared error does not always correlate with…

Zero-shot text-to-speech (TTS) synthesis aims to clone any unseen speaker's voice without adaptation parameters. By quantizing speech waveform into discrete acoustic tokens and modeling these tokens with the language model, recent language…

Deep neural network based speech enhancement technique focuses on learning a noisy-to-clean transformation supervised by paired training data. However, the task-specific evaluation metric (e.g., PESQ) is usually non-differentiable and can…

Sound · Computer Science 2023-02-24 Chen Chen , Yuchen Hu , Weiwei Weng , Eng Siong Chng

Personalized speech enhancement (PSE) is a real-time SE approach utilizing a speaker embedding of a target person to remove background noise, reverberation, and interfering voices. To deploy a PSE model for full duplex communications, the…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-29 Sefik Emre Eskimez , Takuya Yoshioka , Alex Ju , Min Tang , Tanel Parnamaa , Huaming Wang