English
Related papers

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

200 papers

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across…

Sound · Computer Science 2026-03-24 Ro-hoon Oh , Jihwan Seol , Bugeun Kim

Automatic Speech Scoring (ASS) is the computer-assisted evaluation of a candidate's speaking proficiency in a language. ASS systems face many challenges like open grammar, variable pronunciations, and unstructured or semi-structured…

Audio and Speech Processing · Electrical Eng. & Systems 2021-09-07 Yaman Kumar Singla , Avykat Gupta , Shaurya Bagga , Changyou Chen , Balaji Krishnamurthy , Rajiv Ratn Shah

Recent speaker extraction methods using deep non-linear spatial filtering perform exceptionally well when the target direction is known and stationary. However, spatially dynamic scenarios are considerably more challenging due to…

Audio and Speech Processing · Electrical Eng. & Systems 2025-05-21 Jakob Kienegger , Timo Gerkmann

Speaker embedding extractors (EEs), which map input audio to a speaker discriminant latent space, are of paramount importance in speaker diarisation. However, there are several challenges when adopting EEs for diarisation, from which we…

Target speaker extraction aims to extract the speech of a specific speaker from a multi-talker mixture as specified by an auxiliary reference. Most studies focus on the scenario where the target speech is highly overlapped with the…

Sound · Computer Science 2023-09-18 Junjie Li , Ruijie Tao , Zexu Pan , Meng Ge , Shuai Wang , Haizhou Li

Speech recognition and speech synthesis models are typically trained separately, each with its own set of learning objectives, training data, and model parameters, resulting in two distinct large networks. We propose a parameter-efficient…

Computation and Language · Computer Science 2024-10-25 Hawau Olamide Toyin , Hao Li , Hanan Aldarmaki

Argument structure extraction (ASE) aims to identify the discourse structure of arguments within documents. Previous research has demonstrated that contextual information is crucial for developing an effective ASE model. However, we observe…

Computation and Language · Computer Science 2023-10-10 Yun Luo , Zhen Yang , Fandong Meng , Yingjie Li , Jie Zhou , Yue Zhang

Previous works on neural text-to-speech (TTS) have been addressed on limited speed in training and inference time, robustness for difficult synthesis conditions, expressiveness, and controllability. Although several approaches resolve some…

Audio and Speech Processing · Electrical Eng. & Systems 2021-06-28 Keon Lee , Kyumin Park , Daeyoung Kim

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-02 Zili Huang , Desh Raj , Paola García , Sanjeev Khudanpur

This paper introduces an area-based source separation method designed for virtual meeting scenarios. The aim is to preserve speech signals from an unspecified number of sources within a defined spatial area in front of a linear microphone…

Audio and Speech Processing · Electrical Eng. & Systems 2024-08-20 Martin Strauss , Okan Köpüklü

We propose a speaker selection mechanism (SSM) for the training of an end-to-end beamforming neural network, based on recent findings that a listener usually looks to the target speaker with a certain undershot angle. The mechanism allows…

Audio and Speech Processing · Electrical Eng. & Systems 2025-03-25 Luan Vinícius Fiorio , Bruno Defraene , Johan David , Alex Young , Frans Widdershoven , Wim van Houtum , Ronald M. Aarts

In conventional sound event detection (SED) models, two types of events, namely, those that are present and those that do not occur in an acoustic scene, are regarded as the same type of events. The conventional SED methods cannot…

Sound · Computer Science 2021-02-11 Noriyuki Tonami , Keisuke Imoto , Yuki Okamoto , Takahiro Fukumori , Yoichi Yamashita

Speaker clustering is the task of identifying the unique speakers in a set of audio recordings (each belonging to exactly one speaker) without knowing who and how many speakers are present in the entire data, which is essential for speaker…

Sound · Computer Science 2025-09-30 Chaohao Lin , Xu Zheng , Kaida Wu , Peihao Xiang , Ou Bai

Most sound event detection (SED) systems perform well on clean datasets but degrade significantly in noisy environments. Language-queried audio source separation (LASS) models show promise for robust SED by separating target events;…

Sound · Computer Science 2025-08-12 Yuanjian Chen , Yang Xiao , Han Yin , Yadong Guan , Xubo Liu

Speaker extraction aims to extract target speech signal from a multi-talker environment with interference speakers and surrounding noise, given the target speaker's reference information. Most speaker extraction systems achieve satisfactory…

Audio and Speech Processing · Electrical Eng. & Systems 2022-08-12 Chengyun Deng , Shiqian Ma , Yi Zhang , Yongtao Sha , Hui Zhang , Hui Song , Xiangang Li

Recent years have seen a surge in the number of available frameworks for speech enhancement (SE) and recognition. Whether model-based or constructed via deep learning, these frameworks often rely in isolation on either time-domain signals…

Sound · Computer Science 2021-06-01 Sherif Abdulatif , Karim Armanious , Jayasankar T. Sajeev , Karim Guirguis , Bin Yang

In this paper, we provide a new perspective on self-supervised speech models from how the training targets are obtained. We generalize the targets extractor into Offline Targets Extractor (Off-TE) and Online Targets Extractor (On-TE). Based…

Computation and Language · Computer Science 2023-06-01 Ziyang Ma , Zhisheng Zheng , Changli Tang , Yujin Wang , Xie Chen

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts…

Machine Learning · Computer Science 2022-11-08 Itai Gat , Hagai Aronowitz , Weizhong Zhu , Edmilson Morais , Ron Hoory

A Prompt-based Text-To-Speech model allows a user to control different aspects of speech, such as speaking rate and perceived gender, through natural language instruction. Although user-friendly, such approaches are on one hand constrained:…

Computation and Language · Computer Science 2025-07-14 Atli Sigurgeirsson , Simon King

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker…

Audio and Speech Processing · Electrical Eng. & Systems 2023-11-02 Tianchi Liu , Kong Aik Lee , Qiongqiong Wang , Haizhou Li
‹ Prev 1 8 9 10 Next ›