Fake audio clips are a serious concern; effective detection methods are essential.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSA new method improves the accuracy of detecting synthetic audio.
― 5 min read
A new method for separating and manipulating musical sounds.
― 5 min read
SSL-TTS simplifies voice synthesis using minimal training data for high-quality results.
― 6 min read
New methods enhance ASR models for multiple languages, preserving past knowledge.
― 5 min read
A new approach enhances recognition of code-switched phrases in bilingual speech.
― 5 min read
An innovative system automates sound generation for films and games.
― 8 min read
New methods improve speaker recognition in noisy environments.
― 5 min read
New model improves voice conversion, especially for whispered speech and real-time applications.
― 6 min read
Exploring a new digital approach to guitar amplifier sound modeling.
― 5 min read
Introducing a groundbreaking system to generate Hindustani vocal music.
― 6 min read
A new method for accurately modeling optical compressors using neural networks.
― 7 min read
WhisperMask captures voice clearly in noisy places, enhancing communication.
― 6 min read
New methods improve voice quality assessments for patients with vocal system issues.
― 6 min read
VoiceX simplifies the process of creating personalized voices for various applications.
― 4 min read
Examining how voice patterns affect meaning and technology performance.
― 4 min read
NEST offers a faster, more efficient approach to self-supervised speech tasks.
― 5 min read
A look into bias measurement methods for speaker verification.
― 5 min read
Current benchmarks misjudge models' ability to connect audio and visual data.
― 5 min read
New algorithms improve accuracy in identifying musical note beginnings.
― 6 min read
Wav2Small enhances emotion detection in speech with reduced resource needs.
― 5 min read
A look into the complexities of identifying mixed audio tracks.
― 6 min read
New methods improve speech recognition for whispered communication.
― 5 min read
An overview of Tamil's rich dialects and identification methods.
― 5 min read
DUSTED improves efficiency in identifying spoken words by analyzing phonetic patterns.
― 5 min read
A new method improves sound recognition with less computing power.
― 5 min read
A new approach to detect machine issues without compromising data privacy.
― 5 min read
VoiceTailor transforms TTS systems for efficient, personalized voice outputs.
― 5 min read
Learn how sound spreads in spaces and its applications.
― 6 min read
StyleSpeech advances TTS systems by capturing natural speech nuances.
― 6 min read
Examining methods to improve speech clarity in noisy settings through deep learning.
― 5 min read
DualSpeech model improves TTS clarity and speaker resemblance.
― 6 min read
Introducing SONICS, a dataset designed to identify AI-generated music accurately.
― 8 min read
New methods improve detection of fake audio in real-world conditions.
― 4 min read
A new method improves speech recognition for Hindi using pseudo-labeling techniques.
― 4 min read
Research proposes better ways to assess late reverberation in rooms.
― 5 min read
EmoAttack leverages emotional voice conversion to exploit vulnerabilities in speech systems.
― 5 min read
This article reviews techniques for automatic analysis of meerkat vocal sounds.
― 6 min read
Discover how transformers are reshaping speech recognition systems globally.
― 7 min read
A new model separates timbre and structure for better audio creation.
― 7 min read