Related papers: Duration Aware Scheduling for ASR Serving Under Wo…

Automatic Speech Recognition (ASR) has reached impressive accuracy for high-resource languages, yet its utility in linguistic fieldwork remains limited. Recordings collected in fieldwork contexts present unique challenges, including…

Multiserver jobs, which are jobs that occupy multiple servers simultaneously during service, are prevalent in today's computing clusters. But little is known about the delay performance of systems with multiserver jobs. We consider queueing…

End-to-end automatic speech recognition (ASR) models, including both attention-based models and the recurrent neural network transducer (RNN-T), have shown superior performance compared to conventional systems. However, previous studies…

Large Language Models (LLMs) such as GPT-4 and Llama3 can already comprehend complex commands and process diverse tasks. This advancement facilitates their application in controlling drones and robots for various tasks. However, existing…

Large language model (LLM)-based automatic speech recognition (ASR) achieves strong performance but often incurs high computational costs. This work investigates how to obtain the best LLM-ASR performance efficiently. Through comprehensive…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems.…

Large language model (LLM) serving faces the dual challenge of meeting strict user-specific service-level objectives (SLOs) while minimizing computational cost under dynamic, multi-task workloads. Existing approaches either rely on static…

The assessment of a job's Quality of Service (QoS) often revolves around its flow time, also referred to as response time. This study delves into two fundamental objectives for scheduling jobs: the average flow time and the maximum flow…

Serving Large Language Models (LLMs) can benefit immensely from parallelizing both the model and input requests across multiple devices, but incoming workloads exhibit substantial spatial and temporal heterogeneity. Spatially, workloads…

Formal thought disorder (FTD), a hallmark of schizophrenia spectrum disorders, manifests as incoherent speech and poses challenges for clinical assessment. Traditional clinical rating scales, though validated, are resource-intensive and…

The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…

Automatic speech recognition (ASR) of single channel far-field recordings with an unknown number of speakers is traditionally tackled by cascaded modules. Recent research shows that end-to-end (E2E) multi-speaker ASR models can achieve…

Self-supervised learning (SSL) has transformed speech processing, yet its reliance on massive pre-training datasets remains a bottleneck. While robustness is often attributed to scale and diversity, the role of the data distribution is less…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

As augmented large language models (LLMs) with external tools become increasingly popular in web applications, improving augmented LLM inference serving efficiency and optimizing service-level objectives (SLOs) are critical for enhancing…

In the last decade of automatic speech recognition (ASR) research, the introduction of deep learning brought considerable reductions in word error rate of more than 50% relative, compared to modeling without deep learning. In the wake of…

Recently, a few novel streaming attention-based sequence-to-sequence (S2S) models have been proposed to perform online speech recognition with linear-time decoding complexity. However, in these models, the decisions to generate tokens are…

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…

Large language model (LLM) inference serving systems are essential to various LLM-based applications. As demand for LLM services continues to grow, scaling these systems to handle high request rates while meeting latency Service-Level…