A novel method improves voice recognition accuracy across multiple languages.
― 5 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSExploring a new approach to improving speech quality using time-context windowing.
― 5 min read
Recent methods improve audio watermarking for better sound quality and copyright management.
― 5 min read
A new method for improving real-time voice conversion quality.
― 6 min read
SALSA enhances speech recognition accuracy for low-resource languages by integrating ASR and language models.
― 5 min read
New methods improve the quality of speech synthesis in TTS systems.
― 4 min read
Examining the performance of automatic speech recognition for deaf and hard of hearing users.
― 11 min read
A new model transforms plain texts into fitting song lyrics.
― 6 min read
This study analyzes how diphthongs and monophthongs differ in production and movement.
― 5 min read
New method enhances ASR accuracy using language models for better transcriptions.
― 4 min read
A new system corrects speaker identification errors for clearer conversation transcripts.
― 7 min read
SelectTTS simplifies speech generation for unseen speakers with effective frame selection.
― 5 min read
Improving speech clarity through hybrid filterbanks and neural networks.
― 5 min read
AASIST3 improves fake voice detection in automatic speaker verification systems.
― 6 min read
X-Codec improves audio generation by integrating semantic understanding into processing.
― 6 min read
Researchers enhance gesture recognition using innovative learning techniques.
― 6 min read
Portable system reduces construction noise, enhancing worker comfort and community well-being.
― 5 min read
New models like FluxMusic improve music creation from written text.
― 5 min read
This article discusses the benefits of merging voice and facial recognition systems.
― 5 min read
A new model enhances speech recognition by combining audio and visual inputs effectively.
― 5 min read
New models improve accuracy in detecting depression via voice recordings.
― 6 min read
A new method improves speech model performance across various tasks.
― 6 min read
A new method improves keyword spotting accuracy using unlabeled audio data.
― 6 min read
Research shows speech analysis can aid in early detection of Mild Cognitive Impairment.
― 5 min read
A new method improves music generation by focusing on chords and representation.
― 6 min read
Researchers create LibriheavyMix to improve speech recognition in noisy environments.
― 5 min read
New methods improve speech recognition in challenging multi-speaker situations.
― 4 min read
A groundbreaking dataset enhances AI tools for diagnosing heart conditions.
― 7 min read
A new system helps bring Taiwanese Hakka language back to life.
― 5 min read
New methods improve speech clarity in noisy environments using advanced technologies.
― 5 min read
New methods improve voice separation in noisy environments.
― 5 min read
This article explores methods for improving text-to-speech systems for underrepresented languages.
― 6 min read
This study examines how melody varies and connects across different cultures.
― 6 min read
A framework using large language models to create authentic audio dialogues.
― 6 min read
A new benchmark aids in assessing speech tokenizers for better performance.
― 6 min read
A new method improves automatic speech recognition by preserving sound order in knowledge transfer.
― 4 min read
A new model improves speech recognition in multilingual conversations.
― 5 min read
This study examines the effectiveness of LLMs in musicology and their reliability.
― 5 min read
This study examines how noise can enhance speech recognition resilience against challenges.
― 5 min read
Discover how an additional microphone enhances sound direction detection in noisy environments.
― 5 min read