Research explores the use of speech recognition in police body camera footage analysis.
― 6 min read
Electrical Engineering and Systems Science - Audio and Speech Processing
RSSNew methods improve short-duration voice stress detection accuracy.
― 6 min read
A look at how computers are changing music composition.
― 4 min read
New techniques enhance emotional understanding in speech processing tasks.
― 6 min read
New model LinDiff improves speech synthesis speed and quality.
― 4 min read
A new approach to audio compression reduces file size without losing quality.
― 5 min read
Techniques to improve speech recognition amidst background noise.
― 5 min read
Multimodal language understanding enhances voice assistant performance in real-world conditions.
― 5 min read
HiddenSinger improves singing voice quality using advanced AI techniques.
― 5 min read
New methods improve speech clarity for electrolarynx users.
― 6 min read
Researchers blend visual and sound features to improve speech for electrolarynx users.
― 5 min read
A study highlights how ageing affects automatic speaker verification performance.
― 5 min read
PauseSpeech enhances TTS systems with natural-sounding speech through improved pausing.
― 5 min read
This research introduces a system for matching music to video content effectively.
― 6 min read
New methods improve automatic speech recognition performance amid background noise.
― 5 min read
This research highlights how LLMs enhance speech understanding in long videos.
― 4 min read
A new method optimizes speech models for better performance with fewer resources.
― 5 min read
A fresh approach improves how we assess spatial audio quality.
― 5 min read
A study on how to tell apart read and spontaneous speech.
― 6 min read
A new model enhances the realism of synthetic speech.
― 8 min read
Malafide introduces sophisticated spoofing techniques, complicating countermeasures in speech recognition.
― 5 min read
A new model improves accuracy and efficiency in tracking sound sources.
― 5 min read
A new dataset enhances spoken language understanding for Italian.
― 6 min read
MCR-Data2vec 2.0 enhances speech recognition by improving model consistency.
― 4 min read
EM-Network enhances sequence learning in speech and language processing tasks.
― 5 min read
New methods improve multilingual speech recognition using existing data sources.
― 6 min read
Research focuses on enhancing speech tech for languages lacking sufficient data.
― 6 min read
A look at recent developments in improving audio clarity using advanced models.
― 5 min read
A new dataset aims to classify piano scores by difficulty level.
― 7 min read
Gesper framework enhances speech clarity in noisy environments.
― 5 min read
This study presents a new method to enhance speech quality using pre-trained models.
― 6 min read
Combining audio, video, and text enhances detection of hate speech.
― 5 min read
This article discusses a new method for building efficient ASR systems.
― 5 min read
A new approach enhances voice recognition directly on smartphones while ensuring user privacy.
― 6 min read
A new method enhances accuracy in identifying speakers during conversations.
― 5 min read
Teams improve animal sound identification with few examples in DCASE challenge.
― 5 min read
Learn about audio tagging systems and their use on Raspberry Pi.
― 5 min read
New techniques improve accuracy and efficiency in identifying cover songs.
― 5 min read
New method improves noise control in 3D spaces.
― 4 min read
CML-TTS enables better text-to-speech systems across seven languages.
― 5 min read