4 papers
Depth through Recurrence: Towards Ultra-Efficient On-Device ASR
Chen Feng, Tianyi Xu, Ramchalam Kinattinkara Ramakrishnan +5
Modern automatic speech recognition (ASR) systems have achieved remarkable accuracy by scaling model depth and capacity, but at the cost of increased memory, energy, and computatio…
Edge-ASR: Towards Low-Bit Quantization of Automatic Speech Recognition Models
Chen Feng, Yicheng Lin, Shaojie Zhuo +4
Recent advances in Automatic Speech Recognition (ASR) have demonstrated remarkable accuracy and robustness in diverse audio applications, such as live transcription and voice comma…
OmniDraft: A Cross-vocabulary, Online Adaptive Drafter for On-device Speculative Decoding
Ramchalam Kinattinkara Ramakrishnan, Zhaocong Yuan, Shaojie Zhuo +4
Speculative decoding generally dictates having a small, efficient draft model that is either pretrained or distilled offline to a particular target model series, for instance, Llam…
Stepping Forward on the Last Mile
Chen Feng, Shaojie Zhuo, Xiaopeng Zhang +3
Continuously adapting pre-trained models to local data on resource constrained edge devices is the for model deployment. However, as models increase in size and…