Related papers: Breaking Down Power Barriers in On-Device Streamin…
Transformer-based models excel in speech recognition. Existing efforts to optimize Transformer inference, typically for long-context applications, center on simplifying attention score calculations. However, streaming speech recognition…
Recent transformer-based ASR models have achieved word-error rates (WER) below 4%, surpassing human annotator accuracy, yet they demand extensive server resources, contributing to significant carbon footprints. The traditional server-based…
With computers getting more and more powerful and integrated in our daily lives, the focus is increasingly shifting towards more human-friendly interfaces, making Automatic Speech Recognition (ASR) a central player as the ideal means of…
Recurrent transducer models have emerged as a promising solution for speech recognition on the current and next generation smart devices. The transducer models provide competitive accuracy within a reasonable memory footprint alleviating…
While current state-of-the-art Automatic Speech Recognition (ASR) systems achieve high accuracy on typical speech, they suffer from significant performance degradation on disordered speech and other atypical speech patterns. Personalization…
The communication between data-generating devices is partially responsible for a growing portion of the world's power consumption. Thus reducing communication is vital, both, from an economical and an ecological perspective. For machine…
Transformer-based speech enhancement models yield impressive results. However, their heterogeneous and complex structure restricts model compression potential, resulting in greater complexity and reduced hardware efficiency. Additionally,…
We describe a comprehensive methodology for developing user-voice personalized automatic speech recognition (ASR) models by effectively training models on mobile phones, allowing user data and models to be stored and used locally. To…
We present a straightforward, non-intrusive adaptive bit rate streaming segment quality selection policy which aims at extending battery lifetime during playback while limiting the impact on the user's quality of experience, thus benefiting…
Modern smartphones possess hardware for audio acquisition and to perform speech processing tasks such as speaker recognition and health assessment. However, energy consumption remains a concern, especially for resource-intensive DNNs. Prior…
With increasingly more powerful compute capabilities and resources in today's devices, traditionally compute-intensive automatic speech recognition (ASR) has been moving from the cloud to devices to better protect user privacy. However, it…
This paper derives optimal spatial scaling and rate control parameters for power-efficient wireless video streaming on portable devices. A video streaming application is studied, which receives a high-resolution and high-quality video…
Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…
The power that machine learning models consume when making predictions can be affected by a model's architecture. This paper presents various estimates of power consumption for a range of different activation functions, a core factor in…
Speaker adaptation techniques provide a powerful solution to customise automatic speech recognition (ASR) systems for individual users. Practical application of unsupervised model-based speaker adaptation techniques to data intensive…
Power management is an expensive and important issue for large computational infrastructures such as datacenters, large clusters, and computational grids. However, measuring energy consumption of scalable systems may be impractical due to…
Speaker-independent speech recognition systems trained with data from many users are generally robust against speaker variability and work well for a large population of speakers. However, these systems do not always generalize well for…
Transformer-based architectures are the most used architectures in many deep learning fields like Natural Language Processing, Computer Vision or Speech processing. It may encourage the direct use of Transformers in the constrained tasks,…
This paper proposes a method to evaluate and model the power consumption of modern virtual reality playback and streaming applications on smartphones. Due to the high computational complexity of the virtual reality processing toolchain, the…
Nowadays, the use of mobile applications and terminals faces fundamental challenges related to energy constraint. This is due to the limited battery lifetime as compared to the increasing hardware evolution. Video streaming is one of the…