Related papers: Real time spectrogram inversion on mobile phone

The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode, where it generates partial hypotheses before the complete…

Applying large pre-trained speech models like Whisper has shown promise in reducing training costs for various speech tasks. However, integrating these models into streaming systems remains a challenge. This paper presents a novel…

This study presents a systematic comparison of three approaches for the analysis of mental health text using large language models (LLMs): prompt engineering, retrieval augmented generation (RAG), and fine-tuning. Using LLaMA 3, we evaluate…

Sign Language Translation (SLT) converts sign language videos into spoken-language text, bridging communication between Deaf and hearing communities. Current gloss-free approaches rely on large encoder-decoder models, limiting deployment.…

Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high…

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…

Following the success in language domain, the self-attention mechanism (transformer) is adopted in the vision domain and achieving great success recently. Additionally, as another stream, multi-layer perceptron (MLP) is also explored in the…

The escalating scale of Large Language Models (LLMs) necessitates efficient adaptation techniques. Model merging has gained prominence for its efficiency and controllability. However, existing merging techniques typically serve as post-hoc…

Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV…

In this paper, a neural network based real-time speech recognition (SR) system is developed using an FPGA for very low-power operation. The implemented system employs two recurrent neural networks (RNNs); one is a speech-to-character RNN…

Conventional image sensors digitize high-resolution images at fast frame rates, producing a large amount of data that needs to be transmitted off the sensor for further processing. This is challenging for perception systems operating on…

Long-sequence streaming 3D reconstruction remains a significant open challenge. Existing autoregressive models often fail when processing long sequences because they anchor poses to the first frame, leading to attention decay, scale drift,…

Diffusion-based generative models have greatly impacted the speech processing field in recent years, exhibiting high speech naturalness and spawning a new research direction. Their application in real-time communication is, however, still…

In high-energy physics, the increasing luminosity and detector granularity at the Large Hadron Collider are driving the need for more efficient data processing solutions. Machine Learning has emerged as a promising tool for reconstructing…

In speech enhancement (SE), phase estimation is important for perceptual quality, so many methods take clean speech's complex short-time Fourier transform (STFT) spectrum or the complex ideal ratio mask (cIRM) as the learning target. To…

We present Spectron, a novel approach to adapting pre-trained large language models (LLMs) to perform spoken question answering (QA) and speech continuation. By endowing the LLM with a pre-trained speech encoder, our model becomes able to…

In most steganographic methods, increasing in the capacity leads to decrease in the quality of the stego-image, so in this paper, we propose to combine two existing techniques, Pixel value differencing and Gray Level Modification, to come…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

In this paper, we introduce LDGen, a novel method for integrating large language models (LLMs) into existing text-to-image diffusion models while minimizing computational demands. Traditional text encoders, such as CLIP and T5, exhibit…

Extremely large-scale multiple-input-multiple-output (XL-MIMO) is a promising technique to achieve ultra-high spectral efficiency for future 6G communications. The mixed line-of-sight (LoS) and non-line-of-sight (NLoS) XL-MIMO near-field…