Latest Articles for Speech Recognition

Learn how dereverberation boosts speech recognition in noisy environments.

A new model improves understanding of speech and sounds simultaneously.

Enhancing speech models to better recognize and adapt to different accents.

A project to enhance speech recognition across diverse Indian languages.

Kallaama creates a speech dataset in local languages to aid Senegalese farmers.

Indigenous languages face challenges in technology while offering rich cultural insights.

A study on the use of ARI in a gerontological day-care facility.

Research identifies and classifies Sorani Kurdish dialects using extensive audio recordings.

A new method enhances text recognition accuracy across various applications.

A new system improves robot interactions by filtering overlapping speech.

New methods enhance speech recognition in noisy environments using adaptive techniques.

A new method improves translating mixed-language speech into English.

GigaSpeech 2 offers a vast dataset for low-resource languages to improve speech recognition.

A unique dataset captures children's daily lives to enhance machine learning and understanding of human learning.

Discover how Generative AI is changing the way we create content.

New methods improve accuracy and efficiency in speech recognition systems.

A new model enhances communication for individuals with disabilities using speech recognition and Morse code.

A voice-driven model transforming audio interaction with technology.

A new dataset aims to improve speech capture using body-conduction sensors.

Research presents new methods for evaluating speech recognition systems in Polish.

Researchers improve speech decoding using EEG to help those with speech impairments.

This study assesses speech recognition systems using different languages for oral history.

OpenOmni builds flexible tools for creating and testing conversation agents.

Research focuses on better summarization of spoken conversations across languages.

NEST offers a faster, more efficient approach to self-supervised speech tasks.

Research focuses on predicting errors in speech recognition for better accuracy.

Research improves speech recognition for Hindi with diverse accents.

A novel method improves voice recognition accuracy across multiple languages.

Researchers create LibriheavyMix to improve speech recognition in noisy environments.

This research analyzes Mamba's performance in speech tasks, emphasizing sound reconstruction and recognition.

Researchers develop a dataset to improve speech recognition and analysis techniques.

Efforts to improve speech technology for the under-resourced Faetar language.

A study on using language models for correcting errors in speech recognition systems.

A new method improving speech recognition while ensuring data privacy.

Research reveals the difficulties in speech recognition of police radio transmissions.

WeHelp offers robotic support to enhance daily activities for wheelchair users.

This study addresses challenges in audio language models for low-resource languages.

EVA combines audio and visual signals for better speech recognition accuracy.

Research evaluates connections between speech and language models for improved recognition and translation.

A method to boost automatic speech recognition by blending keyword lists with language models.