Related papers: GPU-Accelerated Viterbi Exact Lattice Decoder for …
Denoising is a core operation in modern video pipelines. In codecs, in-loop filters suppress sensor noise and quantisation artefacts to improve rate-distortion performance; in cinema post-production, denoisers are used for restoration,…
Robot audition, encompassing Sound Source Localization (SSL), Sound Source Separation (SSS), and Automatic Speech Recognition (ASR), enables robots and smart devices to acquire auditory capabilities similar to human hearing. Despite their…
Often, the storage and computational constraints of embeddeddevices demand that a single on-device ASR model serve multiple use-cases / domains. In this paper, we propose aFlexibleTransducer(FlexiT) for on-device automatic speech…
The use of deep neural network for decoding error control code will encounter two problems, namely, the high-precision requirements of the error control code and the complexity of the neural network due to the long code. In this paper, a…
Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…
Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…
In this paper, we review various end-to-end automatic speech recognition algorithms and their optimization techniques for on-device applications. Conventional speech recognition systems comprise a large number of discrete components such as…
As the Large Language Model (LLM) becomes increasingly important in various domains. However, the following challenges still remain unsolved in accelerating LLM inference: (1) Synchronized partial softmax update. The softmax operation…
Increase in the number of antennas in the front-end increases the volume of data to be processed at the back-end. This establishes a need for acceleration in back-end processing. To solve the issue of high volume data processing at…
An on-device DNN-HMM speech recognition system efficiently works with a limited vocabulary in the presence of a variety of predictable noise. In such a case, vocabulary and environment adaptation is highly effective. In this paper, we…
A novel decoding algorithm is developed for general quantum convolutional codes. Exploiting useful ideas from classical coding theory, the new decoder introduces two innovations that drastically reduce the decoding complexity compared to…
This paper presents the design and evaluation of a GPU-accelerated inference pipeline for transformer models using NVIDIA TensorRT with mixed-precision optimization. We evaluate BERT-base (110M parameters) and GPT-2 (124M parameters) across…
Although Transformers have gained success in several speech processing tasks like spoken language understanding (SLU) and speech translation (ST), achieving online processing while keeping competitive performance is still essential for…
This paper addresses end-to-end automatic speech recognition (ASR) for long audio recordings such as lecture and conversational speeches. Most end-to-end ASR models are designed to recognize independent utterances, but contextual…
Real-time semantic segmentation is a challenging task that requires high-accuracy models with low-inference times. Implementing these models on embedded systems is limited by hardware capability and memory usage, which produces bottlenecks.…
For real-time semantic segmentation, how to increase the speed while maintaining high resolution is a problem that has been discussed and solved. Backbone design and fusion design have always been two essential parts of real-time semantic…
Transformer has achieved competitive performance against state-of-the-art end-to-end models in automatic speech recognition (ASR), and requires significantly less training time than RNN-based models. The original Transformer, with…
This paper presents a GPU-accelerated decoder for quantum low-density parity-check (QLDPC) codes that achieves sub-$63$ $\mu$s latency, below the surface code decoder's real-time threshold demonstrated on Google's Willow quantum processor.…
Transformer is a deep learning language model widely used for natural language processing (NLP) services in datacenters. Among transformer models, Generative Pre-trained Transformer (GPT) has achieved remarkable performance in text…
Statistical n-gram language models are widely used for context-biasing tasks in Automatic Speech Recognition (ASR). However, existing implementations lack computational efficiency due to poor parallelization, making context-biasing less…