ESPnet-Codec enhances training and evaluation of neural codecs for audio and speech.
Jiatong Shi, Jinchuan Tian, Yihan Wu
― 7 min read
Computer Science - Sound
RSSExploring methods to adapt RNNs for varying audio sample rates.
Alistair Carson, Alec Wright, Stefan Bilbao
― 6 min read
New model achieves faster speech transcription without sacrificing accuracy.
Yael Segal-Feldman, Aviv Shamsian, Aviv Navon
― 4 min read
Discover how Matryoshka embeddings improve speaker recognition efficiency and flexibility.
Shuai Wang, Pengcheng Zhu, Haizhou Li
― 4 min read
Introducing NanoVoice, a quick and efficient text-to-speech model for personalized audio.
Nohil Park, Heeseung Kim, Che Hyun Lee
― 5 min read
New model VoiceGuider improves TTS for diverse speakers.
Jiheum Yeom, Heeseung Kim, Jooyoung Choi
― 6 min read
A novel method for converting voices across languages while preserving unique characteristics.
Giuseppe Ruggiero, Matteo Testa, Jurgen Van de Walle
― 5 min read
New techniques improve expressive speech quality across different speakers.
Lucas H. Ueda, Leonardo B. de M. M. Marques, Flávio O. Simões
― 5 min read
This article explores the role of perceptual metrics in music genre classification.
Tashi Namgyal, Alexander Hepburn, Raul Santos-Rodriguez
― 4 min read
A new method improves speech and audio processing across multiple tasks.
Xiaoyu Yang, Qiujia Li, Chao Zhang
― 5 min read
A new system enhances speaker identification during discussions with multiple participants.
Ruoyu Wang, Shutong Niu, Gaobin Yang
― 5 min read
A new framework enhances emotional expression in TTS systems.
Kun Zhou, You Zhang, Shengkui Zhao
― 5 min read
Recent findings reveal pressure sensors can be used for eavesdropping.
Yonatan Gizachew Achamyeleh, Mohamad Habib Fakih, Gabriel Garcia
― 4 min read
A new algorithm improves sound event detection using self-supervised learning.
Pengfei Cai, Yan Song, Nan Jiang
― 5 min read
Research focuses on improving methods for detecting realistic fake speech.
Davide Salvi, Viola Negroni, Luca Bondi
― 5 min read
A new method streamlines audio and video creation for better synchronization.
Masato Ishii, Akio Hayakawa, Takashi Shibuya
― 5 min read
Control audio effects using simple language descriptions for easier sound adjustments.
Annie Chu, Patrick O'Reilly, Julia Barnett
― 5 min read
Introducing a new model and benchmark for evaluating multi-audio tasks.
Yiming Chen, Xianghu Yue, Xiaoxue Gao
― 5 min read
A new system models emotional intensity in animated characters for enhanced realism.
Jingyi Xu, Hieu Le, Zhixin Shu
― 6 min read
OpenSep automates audio separation for clearer sound experiences without manual input.
Tanvir Mahmud, Diana Marculescu
― 6 min read
PALM enhances audio recognition by optimizing prompt representation and efficiency.
Asif Hanif, Maha Tufail Agro, Mohammad Areeb Qazi
― 4 min read
Explore how wire turns and gauge impact guitar pickup sound.
Charles Batchelor, Jack Gooding, William Marriott
― 7 min read
A new method improves speech recognition for long recordings.
Hao Yen, Shaoshi Ling, Guoli Ye
― 5 min read
This study analyzes how audio, video, and text work together in speech recognition.
Chen Chen, Xiaolou Li, Zehua Liu
― 7 min read
A new model improves naturalness in text-to-speech systems by analyzing pitch patterns.
Tomilov A. A., Gromova A. Y., Svischev A. N
― 4 min read
A new model enhances speech representation for African languages, boosting inclusivity in technology.
Jesujoba O. Alabi, Xuechen Liu, Dietrich Klakow
― 5 min read
A new model improves music creation using melody and text descriptions.
Shaopeng Wei, Manzhen Wei, Haoyu Wang
― 4 min read
New method for speech language models reduces need for extensive data.
Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu
― 6 min read
Learn how voice conversion works and its exciting applications.
Arip Asadulaev, Rostislav Korst, Vitalii Shutov
― 4 min read
Discover how CCI improves multimedia quality assessments.
Alessandro Ragano, Helard Becerra Martinez, Andrew Hines
― 6 min read
Researchers combine audio and visual cues to detect lies more accurately.
Abdelrahman Abdelwahab, Akshaj Vishnubhatla, Ayaan Vaswani
― 6 min read
A new voice-based network bridges language gaps in emergencies.
Majid Behravan, Elham Mohammadrezaei, Mohamed Azab
― 6 min read
Learn how virtual assistants understand user commands better.
Ognjen, Rudovic, Pranay Dighe
― 6 min read
MACE improves audio captioning by linking sounds to accurate text descriptions.
Satvik Dixit, Soham Deshmukh, Bhiksha Raj
― 5 min read
Using machine learning to forecast audience reaction to song covers.
Aris J. Aristorenas
― 7 min read
A new approach to enhance classification through Angular Distance Distribution Loss.
Antonio Almudévar, Romain Serizel, Alfonso Ortega
― 6 min read
New methods improve communication tools for individuals with speech difficulties.
Macarious Hui, Jinda Zhang, Aanchan Mohan
― 7 min read
Researchers use sound waves to estimate human poses without cameras.
Yusuke Oumi, Yuto Shibata, Go Irie
― 8 min read
New methods using language models enhance sound detection amidst background noise.
Han Yin, Yang Xiao, Jisheng Bai
― 6 min read
Fish-Speech enhances voice technology for a more natural communication experience.
Shijia Liao, Yuxuan Wang, Tianyu Li
― 6 min read