Results 71 to 80 of about 2,146 (182)

AlquistCoder: A Synthetic Data Approach to Training Compact Secure Coding Assistants and Building Security Benchmarks

Computational Intelligence, Volume 42, Issue 4, August 2026.
ABSTRACT Large language models are increasingly used as programming assistants, but their security behavior remains uneven: they may generate code with vulnerable patterns, and they may provide actionable help for malicious requests. This paper introduces AlquistCoder, a compact 3.8B‐parameter coding assistant designed to address both risks through ...
Ondřej Kobza, Adam Černý, Ivan Dostál, Jan Šedivý, Maria Rigaki, Muris Sladić, Sebastian Garcia   +6 more
wiley   +1 more source

Small Language Models: A Systematic Review of Computational Trade‐Offs, Privacy Advantages and Deployment in Intelligent Systems

Expert Systems, Volume 43, Issue 8, August 2026.
ABSTRACT This systematic review synthesizes evidence from 68 studies, including peer‐reviewed journal articles, indexed conference/workshop proceedings and five remaining arXiv preprints published between 2022 and 2025, on small language models (SLMs) as computationally efficient alternatives to large language models (LLMs).
Sena Dikici, Turgay Tugay Bilgin
wiley   +1 more source

Evaluation of Socio‐Technical Mechanisms Shaping AI Scribe Documentation Failures: A Netnographic Study

Journal of Evaluation in Clinical Practice, Volume 32, Issue 5, August 2026.
ABSTRACT Background Artificial Intelligence (AI) scribes are increasingly adopted to address electronic health record (EHR) documentation burden. Although early evaluations report perceived efficiency gains and reduced after‐hours work, findings on documentation quality and safety remain mixed. Reported issues, including omissions, attribution mistakes,
Samuel Atiku, Kehinde Owolanke, Olufisayo Olakotan   +2 more
wiley   +1 more source

Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models

CoRR
Recent advances in Automatic Speech Recognition (ASR) have demonstrated remarkable accuracy and robustness in diverse audio applications, such as live transcription and voice command processing. However, deploying these models on resource-constrained edge devices (e.g., IoT device, wearables) still presents substantial challenges due to strict limits ...
Chen Feng, Yicheng Lin, Shaojie Zhuo, Chenzheng Su, Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Xiaopeng Zhang   +6 more
openaire   +2 more sources

Typhoon ASR Real-time: FastConformer-Transducer for Thai Automatic Speech Recognition

CoRR
Models and datasets are publicly available on https://huggingface.co/collections/typhoon-ai/typhoon-asr-technical-report ; Project Page: https://opentyphoon.ai/model/typhoon-asr ...
Warit Sirichotedumrong, Adisai Na-Thalang, Potsawee Manakul, Pittawat Taveekitworachai, Sittipong Sripaisarnmongkol, Kunat Pipatanakul   +5 more
openaire   +2 more sources

ACOUSTIC SPEECH RECOGNITION FOR MARATHI LANGUAGE USING SPHINX

ICTACT Journal on Communication Technology, 2016
Speech recognition or speech to text processing, is a process of recognizing human speech by the computer and converting into text. In speech recognition, transcripts are created by taking recordings of speech as audio and their text transcriptions ...
Aman Ankit, Sonu Kumar Mishra, Rinaz Shaikh, Chandraketu Kumar Gupta, Prakhar Mathur, Soudamini Pawar, Anil Cherukuri   +6 more
doaj  

Automatic Speech Recognition: A survey of deep learning techniques and approaches

International Journal of Cognitive Computing in Engineering
Significant research has been conducted during the last decade on the application of machine learning for speech processing, particularly speech recognition. However, in recent years, deep learning models have shown promising results for different speech
Harsh Ahlawat, Naveen Aggarwal, Deepti Gupta   +2 more
doaj   +1 more source

SENS-ASR: Semantic Embedding Injection in Neural-transducer for Streaming Automatic Speech Recognition

Proceedings of the Language Resources and Evaluation Conference
Many Automatic Speech Recognition (ASR) applications require streaming processing of the audio data. In streaming mode, ASR systems need to start transcribing the input stream before it is complete, i.e., the systems have to process a stream of inputs with a limited (or no) future context.
Youness Dkhissi, Valentin Vielzeuf, Elys Allesiardo, Anthony Larcher   +3 more
openaire   +2 more sources

Suitability of Speech Files for Automatic Speech Recognition Systems after Noise Reduction Procedures [PDF]

Учёные записки Казанского университета: Серия Физико-математические науки, 2015
The results of the experiments on noise reduction in speech files with further transfer in the Google automatic speech recognition (ASR) system are presented. An original method is developed to identify the intervals containing only noise.
R.Kh. Latypov, E.L. Stolov
doaj  

Enhancing Automatic Speech Recognition With Personalized Models: Improving Accuracy Through Individualized Fine-Tuning

IEEE Access
Automatic speech recognition (ASR) systems have become increasingly popular in recent years due to their ability to convert spoken language into text.
Vitalii Brydinskyi, Dmytro Sabodashko, Yuriy Khoma, Michal Podpora, Alexander Konovalov, Volodymyr Khoma   +5 more
doaj   +1 more source