A new architecture improves sound detection across diverse environments.
Zehao Wang, Haobo Yue, Zhicheng Zhang
― 5 min read
Cutting edge science explained simply
A new architecture improves sound detection across diverse environments.
Zehao Wang, Haobo Yue, Zhicheng Zhang
― 5 min read
A new model improves music generation by focusing on individual instruments.
Zhongweiyang Xu, Debottam Dutta, Yu-Lin Wei
― 5 min read
Introducing DENSE, a method enhancing target speech extraction using dynamic embeddings.
Yiwen Wang, Zeyu Yuan, Xihong Wu
― 6 min read
A novel method improves audio transformation while preserving melody and sound quality.
Michele Mancusi, Yurii Halychanskyi, Kin Wai Cheuk
― 6 min read
This method enhances recognition accuracy for uncommon names in speech outputs.
Ernest Pusateri, Anmol Walia, Anirudh Kashi
― 6 min read
Enhancing spoken word identification through visual cues in under-resourced languages.
Leanne Nortje, Dan Oneata, Herman Kamper
― 7 min read
A new model improves detection of audio deepfakes with continuous learning.
Tuan Duy Nguyen Le, Kah Kuan Teh, Huy Dat Tran
― 5 min read
An overview of audio-visual speaker diarization methods, challenges, and systems.
Victoria Mingote, Alfonso Ortega, Antonio Miguel
― 5 min read
BigCodec improves sound quality in low-bitrate audio transmission.
Detai Xin, Xu Tan, Shinnosuke Takamichi
― 4 min read
New method improves sound capture using circular microphones for better audio quality.
Yue Qiao, Vinay Kothapally, Meng Yu
― 5 min read
This article discusses the benefits of simplifying transformer models for speech tasks.
Teresa Dorszewski, Albert Kjøller Jacobsen, Lenka Tětková
― 4 min read
Sortformer integrates speaker diarization and ASR for improved audio processing.
Taejin Park, Ivan Medennikov, Kunal Dhawan
― 5 min read
A fresh approach to create realistic piano sounds using sound component separation.
Riccardo Simionato, Stefano Fasciani
― 8 min read
ParaEVITS improves emotional expression in TTS through natural language guidance.
Xin Jing, Kun Zhou, Andreas Triantafyllopoulos
― 5 min read
Learn how audio inpainting restores missing parts of signals.
Ondřej Mokrý, Peter Balušík, Pavel Rajmic
― 5 min read
New methods improve understanding of spoken language through innovative dataset.
Lennart Keller, Goran Glavaš
― 5 min read
New methods improve human-robot conversation by enhancing speech clarity.
Yue Li, Koen V. Hindriks, Florian A. Kunneman
― 5 min read
New methods improve access to spoken news by segmenting topics more effectively.
Sakshi Deo Shukla, Pavel Denisov, Tugtekin Turan
― 6 min read
This research analyzes Mamba's performance in speech tasks, emphasizing sound reconstruction and recognition.
Xiangyu Zhang, Jianbo Ma, Mostafa Shahin
― 5 min read
A new method for music tagging using few-shot learning shows promising results.
T. Aleksandra Ma, Alexander Lerch
― 6 min read
FlowSep introduces a fresh method for extracting sounds using language queries.
Yi Yuan, Xubo Liu, Haohe Liu
― 5 min read
SSR-Speech offers new solutions for speech generation and editing.
Helin Wang, Meng Yu, Jiarui Hai
― 5 min read
Advancements in AI make fake audio common, prompting the need for detection.
Hong-Hanh Nguyen-Le, Van-Tuan Tran, Dinh-Thuc Nguyen
― 6 min read
New model enhances speech generation in diverse dialects of pitch-accent languages.
Kazuki Yamauchi, Yuki Saito, Hiroshi Saruwatari
― 5 min read
A new method improves sound localization accuracy while ensuring data privacy.
Xinyuan Qian, Xianghu Yue, Jiadong Wang
― 4 min read
A new method for creating structured pop music using graph-based techniques.
Wen Qing Lim, Jinhua Liang, Huan Zhang
― 6 min read
A new method for improving keyword spotting while retaining learned knowledge.
Tianyi Peng, Yang Xiao
― 5 min read
Researchers develop a dataset to improve speech recognition and analysis techniques.
Xiangyu Zhang, Daijiao Liu, Tianyi Xiao
― 6 min read
SoloAudio improves sound extraction using advanced techniques and synthetic data.
Helin Wang, Jiarui Hai, Yen-Ju Lu
― 5 min read
OpenACE provides a fair benchmark for assessing audio codecs across various conditions.
Jozef Coldenhoff, Niclas Granqvist, Milos Cernak
― 5 min read
A method to identify faults in electric motors through sound analysis and Bayesian neural networks.
Waldemar Bauer, Marta Zagorowska, Jerzy Baranowski
― 5 min read
Speech recognition models are evolving with multi-token prediction for faster responses.
Desh Raj, Gil Keren, Junteng Jia
― 5 min read
Efforts to improve speech technology for the under-resourced Faetar language.
Michael Ong, Sean Robertson, Leo Peckham
― 5 min read
A new zero-shot method enhances voice conversion accuracy and minimizes sound leakage.
Wangjin Zhou, Fengrun Zhang, Yiming Liu
― 5 min read
Study reveals how tones change in everyday Taiwanese Mandarin speech.
Xiaoyun Jin, Mirjam Ernestus, R. Harald Baayen
― 5 min read
New method improves detection of Parkinson's Disease through speech analysis with advanced technology.
Shakeel A. Sheikh, Yacouba Kaloga, Md Sahidullah
― 5 min read
New approach enhances voice isolation in mixed audio settings using discrete tokens.
Beilong Tang, Bang Zeng, Ming Li
― 5 min read
Research links paintings to music by interpreting emotions.
Tanisha Hisariya, Huan Zhang, Jinhua Liang
― 6 min read
A study on using language models for correcting errors in speech recognition systems.
Zhiyuan Tang, Dong Wang, Shen Huang
― 5 min read
FLAMO simplifies audio processing through differentiable techniques and frequency-sampling.
Gloria Dal Santo, Gian Marco De Bortoli, Karolina Prawda
― 6 min read