On the efficient representation and execution of deep acoustic models
원문 초록
In this paper we present a simple and computationally efficient quantization scheme that enables us to reduce the resolution of the parameters of a neural network from 32-bit floating point values to 8-bit integer values. The proposed quantization scheme leads to significant memory savings and enables the use of optimized hardware instructions for integer arithmetic, thus significantly reducing the cost of inference. Finally, we propose a "quantization aware" training process that applies the proposed scheme during network training and find that it allows us to recover most of the loss in accuracy introduced by quantization. We validate the proposed techniques by applying them to a long short-term memory-based acoustic model on an open-ended large vocabulary speech recognition task.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Task-Specific Audio Coding for Machines: Machine-Learned Latent Features Are Codes for That Machine
Bridging the Modality Gap: Softly Discretizing Audio Representation for LLM-based Automatic Speech Recognition
Running Conventional Automatic Speech Recognition on Memristor Hardware: A Simulated Approach
First Steps Towards Voice Anonymization for Code-Switching Speech
MambAttention: Mamba with Multi-Head Attention for Generalizable Single-Channel Speech Enhancement
Splitformer: An improved early-exit architecture for automatic speech recognition on edge devices
토론
이 논문과 연결된 포럼 글이 아직 없습니다.