CML-TTS enables better text-to-speech systems across seven languages.
― 5 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSThis study assesses various models for predicting synthesized speech quality.
― 5 min read
Researchers automate bird sound classification, enhancing accuracy in monitoring species.
― 5 min read
FALL-E creates high-quality sound effects from text descriptions.
― 5 min read
A new method enhances voice conversion for individuals with atypical speech.
― 4 min read
SURT 2.0 improves speech recognition for multiple speakers in real-time settings.
― 5 min read
MARBLE sets a standard for evaluating music AI models across multiple tasks.
― 6 min read
A new method improves the accuracy of identifying bird calls.
― 6 min read
New algorithms enhance audio processing performance across varying sample rates.
― 5 min read
Research explores sound analysis to improve mosquito sorting for disease control.
― 5 min read
Explore two innovative methods for altering vocal timbre using Digital Signal Processing.
― 4 min read
A new method enhances speech recognition technology without losing previously learned knowledge.
― 6 min read
A new model improves music transcription accuracy for multiple instruments.
― 5 min read
A new method combines traditional and deep learning for efficient sound imaging.
― 6 min read
New methods improve realism in audio technologies using physics-informed techniques.
― 6 min read
A new model enhances word learning using audio and images.
― 5 min read
Investigating how voice technology can prevent duplicate patient participation in trials.
― 6 min read
A new dataset helps identify signs of depression and anxiety through speech analysis.
― 6 min read
New method reconstructs sound from brain signals, revealing insights into auditory processing.
― 5 min read
A guide to using AI models for music on the Bela platform.
― 5 min read
A new method evaluates ASR systems without needing reference texts.
― 5 min read
NoRefER offers a new way to assess speech recognition outputs without needing transcripts.
― 6 min read
This article discusses a method to enhance video captioning by incorporating audio.
― 5 min read
A new model improves voice conversion by simplifying speech separation techniques.
― 6 min read
Research aims to combine audio and symbolic data for music similarity analysis.
― 7 min read
New methods enhance speech segmentation in multi-language conversations.
― 6 min read
NoisyILRMA enhances sound extraction from background noise for clearer audio experiences.
― 4 min read
This article discusses the role of self-supervised learning in music technology.
― 5 min read
A new framework improves ASR for low-resource languages and multilingual scalability.
― 5 min read
Personalized ASR systems improve communication for DHH individuals significantly.
― 5 min read
New methods leverage conversational summaries for better speaker recognition.
― 5 min read
Enhancing feedback systems for English learners by addressing the cold start problem.
― 6 min read
Researching methods to locate sound sources from wind turbines for noise reduction.
― 4 min read
Introducing a new model for identifying singing techniques in audio tracks.
― 5 min read
A new model enhances speech extraction using audio and visual information.
― 5 min read
Wespeaker simplifies speaker recognition with user-friendly tools and pretrained models.
― 5 min read
A new method transforms mono signals into engaging stereo experiences.
― 5 min read
A study on improving emotion detection in speech for diverse groups.
― 5 min read
This article discusses enhancing speech recognition using confidence-based ensemble methods.
― 5 min read
Study uses multi-data device to track infant sleep patterns more accurately.
― 4 min read