Related papers: A Distilled Low-Latency Neural Vocoder with Explic…

It is challenging to perform lifelong language learning (LLL) on a stream of different tasks without any performance degradation comparing to the multi-task counterparts. To address this issue, we present Lifelong Language Knowledge…

We present an efficient speech separation neural network, ARFDCN, which combines dilated convolutions, multi-scale fusion (MSF), and channel attention to overcome the limited receptive field of convolution-based networks and the high…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Speech denoising is a generally adopted and impactful task, appearing in many common and everyday-life use cases. Although there are very powerful methods published, most of those are too complex for deployment in everyday and low-resources…

This paper describes a novel knowledge distillation framework that leverages acoustically qualified speech data included in an existing training data pool as privileged information. In our proposed framework, a student network is trained…

With the rapid development of deep learning (DL) in recent years, automatic modulation recognition (AMR) with DL has achieved high accuracy. However, insufficient training signal data in complicated channel environments and large-scale DL…

In this paper, we propose a technique to alleviate the quality degradation caused by collapsed speech segments sometimes generated by the WaveNet vocoder. The effectiveness of the WaveNet vocoder for generating natural speech from acoustic…

Pruning aims to reduce the number of parameters while maintaining performance close to the original network. This work proposes a novel \emph{self-distillation} based pruning strategy, whereby the representational similarity between the…

This study presents a novel approach for knowledge distillation (KD) from a BERT teacher model to an automatic speech recognition (ASR) model using intermediate layers. To distil the teacher's knowledge, we use an attention decoder that…

Audio-visual saliency prediction can draw support from diverse modality complements, but further performance enhancement is still challenged by customized architectures as well as task-specific loss functions. In recent studies, denoising…

Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce…

Most modern text-to-speech architectures use a WaveNet vocoder for synthesizing high-fidelity waveform audio, but there have been limitations, such as high inference time, in its practical application due to its ancestral sampling scheme.…

The deployment and application of Large Language Models (LLMs) is hindered by their memory inefficiency, computational demands, and the high costs of API inferences. Traditional distillation methods, which transfer the capabilities of LLMs…

While large audio-language models (LALMs) have demonstrated state-of-the-art audio understanding, their reasoning capability in complex soundscapes still falls behind large vision-language models (LVLMs). Compared to the visual domain, one…

This paper proposes a cross-modal distillation framework, PartDistill, which transfers 2D knowledge from vision-language models (VLMs) to facilitate 3D shape part segmentation. PartDistill addresses three major challenges in this task: the…

Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds…

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like…

The deep complex convolution recurrent network (DCCRN) achieves excellent speech enhancement performance by utilizing the audio spectrum's complex features. However, it has a large number of model parameters. We propose a smaller model,…

Neural audio/speech coding has recently demonstrated its capability to deliver high quality at much lower bitrates than traditional methods. However, existing neural audio/speech codecs employ either acoustic features or learned blind…

This paper presents a novel neural speech phase prediction model which predicts wrapped phase spectra directly from amplitude spectra. The proposed model is a cascade of a residual convolutional network and a parallel estimation…