A systematic review of Green AI
With the ever‐growing adoption of artificial intelligence (AI)‐based systems, the carbon
footprint of AI is no longer negligible. AI researchers and practitioners are therefore urged to …
footprint of AI is no longer negligible. AI researchers and practitioners are therefore urged to …
Prototyping Methodology of End-to-End Speech Analytics Software
O Romanovskyi, I Iosifov, O Iosifova… - … and Data Science …, 2022 - elibrary.kubg.edu.ua
This paper presents the prototype of end-to-end speech recognition, storage, and
postprocessing tasks to build speech analytics, real-time agent augmentation, and other …
postprocessing tasks to build speech analytics, real-time agent augmentation, and other …
Wav2vec2. 0 on the edge: Performance evaluation
S Gondi - arXiv preprint arXiv:2202.05993, 2022 - arxiv.org
Wav2Vec2. 0 is a state-of-the-art model which learns speech representations through
unlabeled speech data, aka, self supervised learning. The pretrained model is then fine …
unlabeled speech data, aka, self supervised learning. The pretrained model is then fine …
The Development of a Kazakh Speech Recognition Model Using a Convolutional Neural Network with Fixed Character Level Filters
N Kadyrbek, M Mansurova, A Shomanov… - Big Data and Cognitive …, 2023 - mdpi.com
This study is devoted to the transcription of human speech in the Kazakh language in
dynamically changing conditions. It discusses key aspects related to the phonetic structure …
dynamically changing conditions. It discusses key aspects related to the phonetic structure …
A Spiking LSTM Accelerator for Automatic Speech Recognition Application Based on FPGA
Long Short-Term Memory (LSTM) finds extensive application in sequential learning tasks,
notably in speech recognition. However, existing accelerators tailored for traditional LSTM …
notably in speech recognition. However, existing accelerators tailored for traditional LSTM …
Deep Learning Models in Speech Recognition: Measuring GPU Energy Consumption, Impact of Noise and Model Quantization for Edge Deployment
A Chakravarty - arXiv preprint arXiv:2405.01004, 2024 - arxiv.org
Recent transformer-based ASR models have achieved word-error rates (WER) below 4%,
surpassing human annotator accuracy, yet they demand extensive server resources …
surpassing human annotator accuracy, yet they demand extensive server resources …
Software Design Decisions for Greener Machine Learning-based Systems
S Del Rey - Proceedings of the IEEE/ACM 3rd International …, 2024 - dl.acm.org
The widespread integration of Machine Learning (ML) in software systems has brought forth
unprecedented advancements, yet the surge in energy consumption raises ecological …
unprecedented advancements, yet the surge in energy consumption raises ecological …
Automatic Silence Detection Employing Artificial Intelligence for Clinical Context Analyses
A Camilo, O Pérez, V Laura… - 2024 3rd …, 2024 - ieeexplore.ieee.org
Automated speech and pause/silence detection is a crucial task in clinical and pathological
environments, supporting diagnostic processes and providing essential information for …
environments, supporting diagnostic processes and providing essential information for …
Human–machine collaboration in transcription
C Miller, M Jetté, D Kokotov - Journal of AI, Robotics & …, 2022 - ingentaconnect.com
As automatic speech recognition (ASR) has improved, it has become a viable tool for
content transcription. Prior to the use of ASR for this task, content transcription was achieved …
content transcription. Prior to the use of ASR for this task, content transcription was achieved …
[PDF][PDF] A review on green deployment for Edge AI-Abstract.
S del Rey, S Martínez-Fernández… - ICT4S (Doctoral …, 2023 - ceur-ws.org
The convergence of edge computing and Artificial Intelligence, namely Edge AI, offers many
opportunities to the industry for building competitive and innovative business models …
opportunities to the industry for building competitive and innovative business models …