Related papers: Learning to Inference with Early Exit in the Progr…

Early exiting has recently emerged as a promising technique for accelerating large language models (LLMs) by effectively reducing the hardware computation and memory access. In this paper, we present SpecEE, a fast LLM inference engine with…

Early Exit Neural Networks (EENNs) present a solution to enhance the efficiency of neural network deployments. However, creating EENNs is challenging and requires specialized domain knowledge, due to the large amount of additional design…

Large language models have achieved remarkable capabilities, but their practical deployment is hindered by significant computational costs. While adaptive computation methods like early-exiting promise to reduce these costs, they introduce…

Early Exit (EE) techniques have emerged as a means to reduce inference latency in Deep Neural Networks (DNNs). The latency improvement and accuracy in these techniques crucially depend on the criteria used to make exit decisions. We propose…

Building efficient inference framework has gained increasing interests for research community. Early-exit models, a variant of LLMs, improves the inference efficiency of LLMs by skipping rest layers and directly generate output tokens when…

Existing pre-trained language models (PLMs) are often computationally expensive in inference, making them impractical in various resource-limited real-world applications. To address this issue, we propose a dynamic token reduction approach…

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…

Large reasoning models that use long chain-of-thought excel at problem-solving yet waste compute on redundant checks. Curbing this overthinking is hard: training-time length penalties can cripple ability, while inference-time early-exit…

Pre-training with self-supervised models, such as Hidden-unit BERT (HuBERT) and wav2vec 2.0, has brought significant improvements in automatic speech recognition (ASR). However, these models usually require an expensive computational cost…

In this paper, we investigate the usage of large language models (LLMs) to improve the performance of competitive speech recognition systems. Different from previous LLM-based ASR error correction methods, we propose a novel multi-stage…

Increasing the size of large language models (LLMs) has been shown to lead to better performance. However, this comes at the cost of slower and more expensive inference. Early-exiting is a promising approach for improving the efficiency of…

This paper presents recent progress on integrating speech separation and enhancement (SSE) into the ESPnet toolkit. Compared with the previous ESPnet-SE work, numerous features have been added, including recent state-of-the-art speech…

We propose a neural network-based speech enhancement (SE) method called the phase-aware recurrent two stage network (rTSN). The rTSN is an extension of our previously proposed two stage network (TSN) framework. This TSN framework was…

Early exiting is an effective paradigm for improving the inference efficiency of pre-trained language models (PLMs) by dynamically adjusting the number of executed layers for each sample. However, in most existing works, easy and hard…

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the…

Speech enhancement aims to improve the perceptual quality of the speech signal by suppression of the background noise. However, excessive suppression may lead to speech distortion and speaker information loss, which degrades the performance…

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…

Streaming models are an essential component of real-time speech enhancement tools. The streaming regime constrains speech enhancement models to use only a tiny context of future information. As a result, the low-latency streaming setup is…

Most speech enhancement algorithms make use of the short-time Fourier transform (STFT), which is a simple and flexible time-frequency decomposition that estimates the short-time spectrum of a signal. However, the duration of short STFT…

Despite their strong performance on reasoning tasks, large reasoning models (LRMs) often suffer from overthinking, producing unnecessarily long outputs and incurring high end-to-end latency, a significant limitation to their real-world…