Tootfinder

"Men acquire a particular quality by constantly acting in a particular way."
-Aristotle
#acting #coaching #inspiration

Archetype-Aware Predictive Autoscaling with Uncertainty Quantification for Serverless Workloads on Kubernetes
Guilin Zhang, Srinivas Vippagunta, Raghavendra Nandagopal, Suchitra Raman, Jeff Xu, Marcus Pfeiffer, Shree Chatterjee, Ziqi Tan, Wulan Guo, Hailong Jiang
https://arxiv.org/abs/2507.05653

Archetype-Aware Predictive Autoscaling with Uncertainty Quantification for Serverless Workloads on Kubernetes
High-performance extreme computing (HPEC) platforms increasingly adopt serverless paradigms, yet face challenges in efficiently managing highly dynamic workloads while maintaining service-level objectives (SLOs). We propose **AAPA**, an archetype-aware predictive autoscaling system that leverages weak supervision to automatically classify 300\,000\,+ workload windows into four archetypes (PERIODIC, SPIKE, RAMP, STATIONARY\_NOISY) with 99.8\% accuracy. Evaluation on publicly available Azure Func…

Real-Time AI-Driven Pipeline for Automated Medical Study Content Generation in Low-Resource Settings: A Kenyan Case Study
Emmanuel Korir, Eugene Wechuli
https://arxiv.org/abs/2507.05212

Real-Time AI-Driven Pipeline for Automated Medical Study Content Generation in Low-Resource Settings: A Kenyan Case Study
Juvenotes is a real-time AI-driven pipeline that automates the transformation of academic documents into structured exam-style question banks, optimized for low-resource medical education settings in Kenya. The system combines Azure Document Intelligence for OCR and Azure AI Foundry (OpenAI o3-mini) for question and answer generation in a microservices architecture, with a Vue/TypeScript frontend and AdonisJS backend. Mobile-first design, bandwidth-sensitive interfaces, institutional tagging, a…

Requirements for Active Assistance of Natural Questions in Software Architecture
Diogo Lemos, Ademar Aguiar, Neil B. Harrison
https://arxiv.org/abs/2506.23898

Requirements for Active Assistance of Natural Questions in Software Architecture
Natural questions are crucial to shaping key architectural decisions and preserving architectural knowledge. They arise organically during the architectural design process, often resulting from the existing architectural experience of the designer and the distinctive characteristics of the system being designed. However, natural questions are often mismanaged or ignored, which can lead to architectural drift, knowledge loss, inefficient resource use, or poor understandability of the system's ar…

Efficient Multilingual ASR Finetuning via LoRA Language Experts
Jiahong Li, Yiwen Shao, Jianheng Zhuo, Chenda Li, Liliang Tang, Dong Yu, Yanmin Qian
https://arxiv.org/abs/2506.21555

Efficient Multilingual ASR Finetuning via LoRA Language Experts
Recent advancements in deep learning have significantly enhanced multilingual automatic speech recognition (ASR) due to the development of advanced model architectures and available large-scale multilingual datasets. Despite that, multilingual ASR still suffers from the curse of multilinguality in that different languages tend to interfere with each other, making it difficult for the ASR model to identify multiple languages effectively while sharing model capacity across them. This paper propos…

Adaptive Knowledge Distillation for Device-Directed Speech Detection
Hyung Gun Chi, Florian Pesce, Wonil Chang, Oggi Rudovic, Arturo Argueta, Stefan Braun, Vineet Garg, Ahmed Hussen Abdelaziz
https://arxiv.org/abs/2508.02801

Adaptive Knowledge Distillation for Device-Directed Speech Detection
Device-directed speech detection (DDSD) is a binary classification task that separates the user's queries to a voice assistant (VA) from background speech or side conversations. This is important for achieving naturalistic user experience. To this end, we propose knowledge distillation (KD) to enhance DDSD accuracy while ensuring efficient deployment. Specifically, we introduce a novel adaptive KD method that transfers knowledge from general representations of an ASR large pre-trained acoustic …

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
Anyu Ying, Natarajan Balaji Shankar, Chyi-Jiunn Lin, Mohan Shi, Pu Wang, Hye-jin Shim, Siddhant Arora, Hugo Van hamme, Abeer Alwan, Shinji Watanabe
https://arxiv.org/abs/2508.16576

Benchmarking Training Paradigms, Dataset Composition, and Model Scaling for Child ASR in ESPnet
Despite advancements in ASR, child speech recognition remains challenging due to acoustic variability and limited annotated data. While fine-tuning adult ASR models on child speech is common, comparisons with flat-start training remain underexplored. We compare flat-start training across multiple datasets, SSL representations (WavLM, XEUS), and decoder architectures. Our results show that SSL representations are biased toward adult speech, with flat-start training on child speech mitigating the…

Scalable Offline ASR for Command-Style Dictation in Courtrooms
Kumarmanas Nethil, Vaibhav Mishra, Kriti Anandan, Kavya Manohar
https://arxiv.org/abs/2507.01021

Scalable Offline ASR for Command-Style Dictation in Courtrooms
We propose an open-source framework for Command-style dictation that addresses the gap between resource-intensive Online systems and high-latency Batch processing. Our approach uses Voice Activity Detection (VAD) to segment audio and transcribes these segments in parallel using Whisper models, enabling efficient multiplexing across audios. Unlike proprietary systems like SuperWhisper, this framework is also compatible with most ASR architectures, including widely used CTC-based models. Our mult…

TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimization
Nowfel Mashnoor, Mohammad Akyash, Hadi Kamali, Kimia Azar
https://arxiv.org/abs/2507.17962 http…

TimelyHLS: LLM-Based Timing-Aware and Architecture-Specific FPGA HLS Optimization
Achieving timing closure and design-specific optimizations in FPGA-targeted High-Level Synthesis (HLS) remains a significant challenge due to the complex interaction between architectural constraints, resource utilization, and the absence of automated support for platform-specific pragmas. In this work, we propose TimelyHLS, a novel framework integrating Large Language Models (LLMs) with Retrieval-Augmented Generation (RAG) to automatically generate and iteratively refine HLS code optimized for…

Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions
Tina Raissi, Nick Rossenbach, Ralf Schl\"uter
https://arxiv.org/abs/2508.09868

Analysis of Domain Shift across ASR Architectures via TTS-Enabled Separation of Target Domain and Acoustic Conditions
We analyze automatic speech recognition (ASR) modeling choices under domain mismatch, comparing classic modular and novel sequence-to-sequence (seq2seq) architectures. Across the different ASR architectures, we examine a spectrum of modeling choices, including label units, context length, and topology. To isolate language domain effects from acoustic variation, we synthesize target domain audio using a text-to-speech system trained on LibriSpeech. We incorporate target domain n-gram and neural …