Related papers: Adaptive Variable Degree-k Zero-Trees for Re-Encod…

We present a scalable and efficient neural waveform coding system for speech compression. We formulate the speech coding problem as an autoencoding task, where a convolutional neural network (CNN) performs encoding and decoding as a neural…

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality--It…

Recently, end-to-end automatic speech recognition has become the mainstream approach in both industry and academia. To optimize system performance in specific scenarios, the Weighted Finite-State Transducer (WFST) is extensively used to…

Traditional speech enhancement techniques modify the magnitude of a speech in time-frequency domain, and use the phase of a noisy speech to resynthesize a time domain speech. This work proposes a complex-valued Gaussian process latent…

The cost of deploying vision transformers increasingly represents a barrier to wider industrial adoption. Existing compression techniques require additional end-to-end fine-tuning or incur a significant drawback to energy efficiency, making…

This paper investigates the adaptive bitrate (ABR) video semantic communication over wireless networks. In the considered model, video sensing devices must transmit video semantic information to an edge server, to facilitate ubiquitous…

Vision transformer has emerged as a new paradigm in computer vision, showing excellent performance while accompanied by expensive computational cost. Image token pruning is one of the main approaches for ViT compression, due to the facts…

Inspired by recent developments in neural speech coding and diffusion-based language modeling, we tackle speech enhancement by modeling the conditional distribution of clean speech codes given noisy speech codes using absorbing discrete…

For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a…

Future smart factories are expected to deploy an emerging dynamic Virtual Reality (VR) applications with high bandwidth wireless connections in the THz communication bands, where a factory worker can follow activities through 360{\deg}video…

Using audio and text embeddings jointly for Keyword Spotting (KWS) has shown high-quality results, but the key challenge of how to semantically align two embeddings for multi-word keywords of different sequence lengths remains largely…

Inspired by the success of deep neural networks (DNNs) in speech processing, this paper presents Deep Vocoder, a direct end-to-end low bit rate speech compression method with deep autoencoder (DAE). In Deep Vocoder, DAE is used for…

Most of the current deep learning-based approaches for speech enhancement only operate in the spectrogram or waveform domain. Although a cross-domain transformer combining waveform- and spectrogram-domain inputs has been proposed, its…

Visual prompt tuning (VPT), i.e., fine-tuning some lightweight prompt tokens, provides an efficient and effective approach for adapting pre-trained models to various downstream tasks. However, most prior art indiscriminately uses a fixed…

Unsupervised spoken term discovery (UTD) aims at finding recurring segments of speech from a corpus of acoustic speech data. One potential approach to this problem is to use dynamic time warping (DTW) to find well-aligning patterns from the…

High-Frequency (HF) signals are ubiquitous in the industrial world and are of great use for monitoring of industrial assets. Most deep learning tools are designed for inputs of fixed and/or very limited size and many successful applications…

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

In this work, we propose a new mathematical vocoder algorithm(modified spectral inversion) that generates a waveform from acoustic features without phase estimation. The main benefit of using our proposed method is that it excludes the…

Variational quantum eigensolver (VQE), aiming at determining the ground state energy of a quantum system described by a Hamiltonian on noisy intermediate scale quantum (NISQ) devices, is among the most significant applications of…

The primary aim of Audio-Visual Segmentation (AVS) is to precisely identify and locate auditory elements within visual scenes by accurately predicting segmentation masks at the pixel level. Achieving this involves comprehensively…