相关论文: Emformer: Efficient Memory Transformer Based Acous…

Memory constraint of always-on devices is one of the major concerns when deploying speech processing models on these devices. While larger models trained with sufficiently large amount of data generally perform better, making them fit in…

In this paper we present a Transformer-Transducer model architecture and a training technique to unify streaming and non-streaming speech recognition models into one model. The model is composed of a stack of transformer layers for audio…

In our previous work we demonstrated that a single headed attention encoder-decoder model is able to reach state-of-the-art results in conversational speech recognition. In this paper, we further improve the results for both Switchboard 300…

Multi-channel inputs offer several advantages over single-channel, to improve the robustness of on-device speech recognition systems. Recent work on multi-channel transformer, has proposed a way to incorporate such inputs into end-to-end…

Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized…

Transformer models have revolutionized natural language processing, achieving state-of-the-art performance and demonstrating remarkable scalability. However, their memory demands, particularly due to maintaining full context in memory, pose…

Transformer architectures based on the attention mechanism have revolutionized natural language processing (NLP), driving major breakthroughs across virtually every NLP task. However, their substantial memory and computational requirements…

While significant improvements have been made in recent years in terms of end-to-end automatic speech recognition (ASR) performance, such improvements were obtained through the use of very large neural networks, unfit for embedded use on…

The conversion from text to speech relies on the accurate mapping from linguistic to acoustic symbol sequences, for which current practice employs recurrent statistical models like recurrent neural networks. Despite the good performance of…

For streaming speech recognition, a Transformer-based encoder has been widely used with block processing. Although many studies addressed improving emission latency of transducers, little work has been explored for improving encoding…

Entropy estimation is essential for the performance of learned image compression. It has been demonstrated that a transformer-based entropy model is of critical importance for achieving a high compression ratio, however, at the expense of a…

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…

Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank projection methods such as Linformer and kernel-based…

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…

The ability to dynamically adjust the computational load of neural models during inference in a resource aware manner is crucial for on-device processing scenarios, characterised by limited and time-varying computational resources.…

Low power deep learning accelerators on the speech processing enable real-time applications on edge devices. However, most of the existing accelerators suffer from high power consumption and focus on image applications only. This paper…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

This paper introduces a lightweight deep learning model for real-time speech enhancement, designed to operate efficiently on resource-constrained devices. The proposed model leverages a compact architecture that facilitates rapid inference…

Transformer-based language models have achieved remarkable performance across a wide range of tasks, yet their high inference latency poses a significant challenge for real-timeand large-scale deployment. While existing caching…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…