English
Related papers

Related papers: Training Dynamics-Aware Multi-Factor Curriculum Le…

200 papers

Speaker recognition deals with recognizing speakers by their speech. Most speaker recognition systems are built upon two stages, the first stage extracts low dimensional correlation embeddings from speech, and the second performs the…

Universal Speech Enhancement (USE) aims to restore speech quality under diverse degradation conditions while preserving signal fidelity. Despite recent progress, key challenges in training target selection, the distortion--perception…

Speaker embedding extractors significantly influence the performance of clustering-based speaker diarisation systems. Conventionally, only one embedding is extracted from each speech segment. However, because of the sliding window approach,…

Sound · Computer Science 2022-11-09 Hee-Soo Heo , Youngki Kwon , Bong-Jin Lee , You Jin Kim , Jee-weon Jung

Building a single universal speech enhancement (SE) system that can handle arbitrary input is a demanded but underexplored research topic. Towards this ultimate goal, one direction is to build a single model that handles diverse audio…

Audio and Speech Processing · Electrical Eng. & Systems 2024-02-19 Wangyou Zhang , Jee-weon Jung , Shinji Watanabe , Yanmin Qian

Self-supervised speech pre-training empowers the model with the contextual structure inherent in the speech signal while self-supervised text pre-training empowers the model with linguistic information. Both of them are beneficial for…

Sound · Computer Science 2022-11-28 Zhuoyuan Yao , Shuo Ren , Sanyuan Chen , Ziyang Ma , Pengcheng Guo , Lei Xie

Speaker extraction requires a sample speech from the target speaker as the reference. However, enrolling a speaker with a long speech is not practical. We propose a speaker extraction technique, that performs in multiple stages to take full…

Audio and Speech Processing · Electrical Eng. & Systems 2021-04-05 Meng Ge , Chenglin Xu , Longbiao Wang , Eng Siong Chng , Jianwu Dang , Haizhou Li

We propose TES-VC (Text-driven Environment and Speaker controllable Voice Conversion), a text-driven voice conversion framework with independent control of speaker timbre and environmental acoustics. TES-VC processes simultaneous text…

Sound · Computer Science 2025-06-16 Jiawei Jin , Zhihan Yang , Yixuan Zhou , Zhiyong Wu

A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the…

Audio and Speech Processing · Electrical Eng. & Systems 2022-09-01 Zexu Pan , Meng Ge , Haizhou Li

Speaker diarization is a task to label an audio or video recording with the identity of the speaker at each given time stamp. In this work, we propose a novel machine learning framework to conduct real-time multi-speaker diarization and…

Sound · Computer Science 2023-02-23 Baihan Lin , Xinxin Zhang

Visual information can serve as an effective cue for target speaker extraction (TSE) and is vital to improving extraction performance. In this paper, we propose AV-SepFormer, a SepFormer-based attention dual-scale model that utilizes cross-…

Recent speaker diarisation systems often convert variable length speech segments into fixed-length vector representations for speaker clustering, which are known as speaker embeddings. In this paper, the content-aware speaker embeddings…

Sound · Computer Science 2021-02-15 G. Sun , D. Liu , C. Zhang , P. C. Woodland

In recent years, end-to-end approaches have made notable progress in addressing the challenge of speaker diarization, which involves segmenting and identifying speakers in multi-talker recordings. One such approach, Encoder-Decoder…

Sound · Computer Science 2025-06-09 David Palzer , Matthew Maciejewski , Eric Fosler-Lussier

Recent advancements in Text-to-Speech (TTS) systems have enabled the generation of natural and expressive speech from textual input. Accented TTS aims to enhance user experience by making the synthesized speech more relatable to minority…

Audio and Speech Processing · Electrical Eng. & Systems 2024-10-18 Jan Melechovsky , Ambuj Mehrish , Berrak Sisman , Dorien Herremans

Many of the existing TTS systems cannot accurately synthesize text containing a variety of numerical formats, resulting in reduced intelligibility of the synthesized speech. This research aims to develop a numerical format classifier that…

Audio and Speech Processing · Electrical Eng. & Systems 2024-12-03 Yaser Darwesh , Lit Wei Wern , Mumtaz Begum Mustafa

We introduce machine unlearning for speech tasks, a novel and underexplored research problem that aims to efficiently and effectively remove the influence of specific data from trained speech models without full retraining. This has…

Machine Learning · Computer Science 2025-06-03 Jiali Cheng , Hadi Amiri

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

Sound · Computer Science 2018-05-16 Hiroshi Seki , Takaaki Hori , Shinji Watanabe , Jonathan Le Roux , John R. Hershey

It is common knowledge that the quantity and quality of the training data play a significant role in the creation of a good machine learning model. In this paper, we take it one step further and demonstrate that the way the training…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-12 Georgios Karakasidis , Tamás Grósz , Mikko Kurimo

Sound event detection (SED) entails identifying the type of sound and estimating its temporal boundaries from acoustic signals. These events are uniquely characterized by their spatio-temporal features, which are determined by the way they…

Audio and Speech Processing · Electrical Eng. & Systems 2023-05-19 Tanmay Khandelwal , Rohan Kumar Das

A text-to-speech (TTS) model typically factorizes speech attributes such as content, speaker and prosody into disentangled representations.Recent works aim to additionally model the acoustic conditions explicitly, in order to disentangle…

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