Latest Articles for Automatic Speech Recognition

A new method integrates acoustic information into language models for better speech recognition.

LLMs improve accuracy in medical transcriptions, benefiting patient care.

A new system to evaluate audio codec performance across various applications.

An overview of ASR and its advancements in modern applications.

AI is improving cochlear implants for better hearing and communication in challenging environments.

A new method improves speech evaluation using entire recordings.

A new framework for assessing foundation models in speech tasks.

A new method directly creates subtitles, improving accessibility for diverse audiences.

This study evaluates ASR systems' performance with individuals who stutter.

A universal audio clip can mute advanced ASR models like Whisper.

Enhanced speech recognition for classrooms using advanced training techniques improves learning.

New model VPIDM improves clarity of speech in noisy environments.

A new model improves speech recognition using multiple decoding methods.

mHuBERT-147 processes speech in multiple languages efficiently.

Improving accuracy in transcribing scientific presentations through speech and visual integration.

A study on translating Nigerian English for better accessibility in Nollywood films.

New model improves speech-to-text translation using large language models.

Improving speaker anonymization technology for nine languages to ensure privacy.

New method improves ASR systems' handling of various accents through specialized codebooks.

This study evaluates speech technology in low-resource languages like Tunisian Arabic.

Mamba shows promise against transformers in speech tasks, especially for long inputs.

Learn how context improves automatic speech recognition accuracy and word recognition.

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

A study on enhancing transcription accuracy through improved prompt design.

A new model aims to improve speech translation quality through integrated systems.

New methods aim to enhance recognition of whispered speech in automatic systems.

AI models enhance accuracy of speech-to-text conversions.

Research enhances ASR systems using language models for better accuracy.

A new system enhances speech recognition by using contextual keywords for better accuracy.

New methods enhance ASR models for multiple languages, preserving past knowledge.

Examining Automatic Speech Recognition in Canadian court systems and its impact.

Research shows how LLMs enhance automatic speech recognition in Japanese language.

SALSA enhances speech recognition accuracy for low-resource languages by integrating ASR and language models.

Examining the performance of automatic speech recognition for deaf and hard of hearing users.

A new method leverages speech data to improve autism assessments.

Examining the latest developments in generative models across various fields.

A new model combines speech recognition and entity recognition for better results.

A new approach enhances ASR systems for better classroom communication.

This article explores how varied inputs can boost speech recognition accuracy.

Study explores ASR development for Amis and Seediq, focusing on data use.