Electrical Engineering and Systems Science - Audio and Speech Processing

SoundRevolutionizing Sound: The Smooth-Foley Breakthrough

Discover how Smooth-Foley enhances video audio generation.

2025-01-29T15:09:54+00:00 ― 6 min read

Audio and Speech ProcessingCrafting Melodies from Lyrics: A New Method

Innovative technique connects lyrics and melodies for better song creation.

2025-01-29T10:13:48+00:00 ― 7 min read

SoundMastering Turn-Taking in Conversations

Enhancing machine understanding of human dialogue turn-taking dynamics.

2025-01-29T05:17:42+00:00 ― 8 min read

SoundDeepFake Detection: A Multilingual Challenge

Exploring how language affects DeepFake detection accuracy across various languages.

2025-01-28T14:29:24+00:00 ― 6 min read

SoundMeet VERSA: Your Audio Evaluation Companion

VERSA evaluates speech, audio, and music quality effectively.

2025-01-28T09:33:18+00:00 ― 9 min read

SoundAudio-Language Models: A New Frontier

Discover how audio-language models are changing sound recognition technology.

2025-01-27T23:41:06+00:00 ― 6 min read

Computation and LanguageTransforming Conversational Speech Synthesis

New methods enhance natural dialogue in speech technology.

2025-01-27T08:52:48+00:00 ― 6 min read

Computation and LanguageBreaking New Ground in Voice Technology

Discover how SpeechSSM transforms long-form speech generation for better interactions.

2025-01-26T13:08:24+00:00 ― 5 min read

Computation and LanguageBreaking Down Simultaneous Speech-to-Text Translation

Learn how real-time translation transforms communication across languages.

2025-01-25T22:20:06+00:00 ― 6 min read

SoundMeet U-Mamba-Net: The Future of Speech Separation

A lightweight model designed to effectively separate mixed speech in noisy environments.

2025-01-25T12:27:54+00:00 ― 6 min read

SoundGuarding Against Audio Spoofing: The Fight for Voice Security

Researchers tackle audio spoofing to enhance voice recognition security.

2025-01-25T07:31:48+00:00 ― 9 min read

Audio and Speech ProcessingAudiovisual Speech Recognition: A New Frontier

Learn how AV-ASR combines audio and visuals for better speech recognition.

2025-01-24T21:39:36+00:00 ― 6 min read

SoundRevolutionizing Music Learning: LOEV Method Uncovered

A new method is transforming how machines learn from music.

2025-01-24T11:47:24+00:00 ― 7 min read

SoundTurning Silent Signals into Clear Speech

New technology transforms silent murmurs into audible communication for those in need.

2025-01-23T20:59:06+00:00 ― 6 min read

SoundAdvancements in Speech Synthesis with rtMRI Technology

New methods in speech synthesis improve clarity and adaptability for diverse applications.

2025-01-23T16:03:00+00:00 ― 8 min read

Audio and Speech ProcessingEthiopian Chants: A Hidden Musical Treasure

Discover the rich tradition of Ethiopian Orthodox Tewahedo Church chants.

2025-01-23T11:06:54+00:00 ― 7 min read

Audio and Speech ProcessingPreserving Ethiopian Chants: The Yaredawi Zema Dataset

A new dataset highlights the beauty of Ethiopian Orthodox chants.

2025-01-23T06:10:48+00:00 ― 7 min read

Audio and Speech ProcessingImproving Speech Recognition for All

New advances help speech-recognition technology better serve people with speech disorders.

2025-01-23T01:14:42+00:00 ― 6 min read

SoundETTA: Transforming Text into Sound

Discover how ETTA turns words into creative audio experiences.

2025-01-22T10:26:24+00:00 ― 6 min read

SoundFeel the Beat: New Music Emotion Recognition

A fresh take on how music affects our emotions.

2025-01-22T00:34:12+00:00 ― 7 min read

SoundCoheDancers: Redefining Group Dance Creation

A new framework for generating synchronized and natural group dances.

2025-01-21T14:42:00+00:00 ― 8 min read

SoundMachines Learning Emotions Through Mouth Movements

New approach in emotion recognition focuses on mouth movements over sounds.

2025-01-20T23:53:42+00:00 ― 6 min read

SoundTransforming Voice Synthesis with Stable-TTS

Discover how Stable-TTS improves text-to-speech technology for a human-like experience.

2025-01-19T18:17:06+00:00 ― 7 min read

Human-Computer InteractionMeasuring Walking Speed Indoors with Sound Waves

Innovative sound wave technology offers new insights into indoor walking speed.

2025-01-19T13:21:00+00:00 ― 6 min read

Machine LearningThe Future of Audio Assistants: AQA-K

Audio assistants are getting smarter with AQA-K, enhancing responses through knowledge.

2025-01-18T22:32:42+00:00 ― 6 min read

Neurons and CognitionDecoding the Brain's Role in Speech

Researchers study how our brain controls speech and its implications for recovery.

2025-01-18T05:35:46+00:00 ― 6 min read

SoundThe Rise of Text-to-Audio Technology

Discover how text can transform into audio with cutting-edge models.

2025-01-17T21:52:12+00:00 ― 3 min read