English
Related papers

Related papers: Voices Obscured in Complex Environmental Settings …

200 papers

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Computation and Language · Computer Science 2021-10-15 Ian Palmer , Andrew Rouditchenko , Andrei Barbu , Boris Katz , James Glass

In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment…

Sound · Computer Science 2025-10-24 Junjie Zheng , Gongyu Chen , Chaofan Ding , Zihao Chen

This paper focuses on designing a noise-robust end-to-end Audio-Visual Speech Recognition (AVSR) system. To this end, we propose Visual Context-driven Audio Feature Enhancement module (V-CAFE) to enhance the input noisy audio speech with a…

Sound · Computer Science 2022-07-14 Joanna Hong , Minsu Kim , Daehun Yoo , Yong Man Ro

Whisper generation is constrained by the difficulty of data collection. Because whispered speech has low acoustic amplitude, high-fidelity recording is challenging. In this paper, we introduce WhispSynth, a large-scale multilingual corpus…

Sound · Computer Science 2026-03-17 Tianyi Tan , Jiaxin Ye , Yuanming Zhang , Xiaohuai Le , Xianjun Xia , Chuanzeng Huang , Jing Lu

Privacy in speech and audio has many facets. A particularly under-developed area of privacy in this domain involves consideration for information related to content and context. Speech content can include words and their meaning or even…

Audio and Speech Processing · Electrical Eng. & Systems 2023-01-24 Jennifer Williams , Karla Pizzi , Shuvayanti Das , Paul-Gauthier Noe

Accurate far-field speech datasets are critical for tasks such as automatic speech recognition (ASR), dereverberation, speech enhancement, and source separation. However, current datasets are limited by the trade-off between acoustic…

Audio and Speech Processing · Electrical Eng. & Systems 2025-10-28 Sarabeth S. Mullins , Georg Götz , Eric Bezzam , Steven Zheng , Daniel Gert Nielsen

Conventional approaches to sound localization and separation are based on microphone arrays in artificial systems. Inspired by the selective perception of human auditory system, we design a multi-source listening system which can separate…

Sound · Computer Science 2019-11-11 Xuecong Sun , Han Jia , Zhe Zhang , Yuzhen Yang , Zhaoyong Sun , Jun Yang

Multi-Modal automatic speech recognition (ASR) techniques aim to leverage additional modalities to improve the performance of speech recognition systems. While existing approaches primarily focus on video or contextual information, the…

Sound · Computer Science 2023-12-27 Haoxu Wang , Fan Yu , Xian Shi , Yuezhang Wang , Shiliang Zhang , Ming Li

The widespread adoption of voice-activated systems has modified routine human-machine interaction but has also introduced new vulnerabilities. This paper investigates the susceptibility of automatic speech recognition (ASR) algorithms in…

Cryptography and Security · Computer Science 2024-04-09 Forrest McKee , David Noever

Conditional diffusion models have the generative controllability by incorporating external conditions. However, their performance significantly degrades with noisy conditions, such as corrupted labels in the image generation or unreliable…

Machine Learning · Computer Science 2025-10-14 Xin Chen , Gillian Dobbie , Xinyu Wang , Feng Liu , Di Wang , Jingfeng Zhang

We present DRES: a 1.5-hour Dutch realistic elicited (semi-spontaneous) speech dataset from 80 speakers recorded in noisy, public indoor environments. DRES was designed as a test set for the evaluation of state-of-the-art (SOTA) automatic…

Audio and Speech Processing · Electrical Eng. & Systems 2026-03-11 Dimme de Groot , Yuanyuan Zhang , Jorge Martinez , Odette Scharenborg

Systematic evaluation of speech separation and enhancement models under moving sound source conditions requires extensive and diverse data. However, real-world datasets often lack sufficient data for training and evaluation, and synthetic…

Sound · Computer Science 2025-03-07 Kai Li , Wendi Sang , Chang Zeng , Runxuan Yang , Guo Chen , Xiaolin Hu

Humans use context to assess the veracity of information. However, current audio deepfake detectors only analyze the audio file without considering either context or transcripts. We create and analyze a Journalist-provided Deepfake Dataset…

Audio-visual speech enhancement (AVSE) is a task that uses visual auxiliary information to extract a target speaker's speech from mixed audio. In real-world scenarios, there often exist complex acoustic environments, accompanied by various…

Sound · Computer Science 2025-11-03 Jiarong Du , Zhan Jin , Peijun Yang , Juan Liu , Zhuo Li , Xin Liu , Ming Li

This paper describes the Spot the Difference Corpus which contains 54 interactions between pairs of subjects interacting to find differences in two very similar scenes. The setup used, the participants' metadata and details about collection…

Computation and Language · Computer Science 2018-05-15 José Lopes , Nils Hemmingsson , Oliver Åstrand

We present an iVector based Acoustic Scene Classification (ASC) system suited for real life settings where active foreground speech can be present. In the proposed system, each recording is represented by a fixed-length iVector that models…

Audio and Speech Processing · Electrical Eng. & Systems 2021-08-03 Siyuan Song , Brecht Desplanques , Celest De Moor , Kris Demuynck , Nilesh Madhu

Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview…

Computation and Language · Computer Science 2020-04-08 Bodhisattwa Prasad Majumder , Shuyang Li , Jianmo Ni , Julian McAuley

In crowded settings, the human brain can focus on speech from a target speaker, given prior knowledge of how they sound. We introduce a novel intelligent hearable system that achieves this capability, enabling target speech hearing to…

Sound · Computer Science 2024-05-31 Bandhav Veluri , Malek Itani , Tuochao Chen , Takuya Yoshioka , Shyamnath Gollakota

In the highly constrained context of low-resource language studies, we explore vector representations of speech from a pretrained model to determine their level of abstraction with regard to the audio signal. We propose a new unsupervised…

Computation and Language · Computer Science 2024-02-09 Maxime Fily , Guillaume Wisniewski , Severine Guillaume , Gilles Adda , Alexis Michaud

Virtual acoustic environments enable the creation and simulation of realistic and eco-logically valid daily-life situations vital for hearing research and audiology. Reverberant indoor environments are particularly important. For real-time…

Audio and Speech Processing · Electrical Eng. & Systems 2025-12-03 Stefan Fichna , Steven van de Par , Bernhard U. Seeber , Stephan D. Ewert