Related papers: CodecSlime: Temporal Redundancy Compression of Neu…
A deep neural network solution for time-scale modification (TSM) focused on large stretching factors is proposed, targeting environmental sounds. Traditional TSM artifacts such as transient smearing, loss of presence, and phasiness are…
Recurrent neural networks have a strong inductive bias towards learning temporally compressed representations, as the entire history of a sequence is represented by a single vector. By contrast, Transformers have little inductive bias…
In this study, we focus on nonlinear compression methods in spectral features for speaker verification based on deep neural network. We consider different kinds of channel-dependent (CD) nonlinear compression methods optimized in a…
Ultra-low-bitrate speech coding is pivotal for bandwidth-constrained communication and deep compression, yet maintaining naturalness and speaker identity at such extreme bit budgets remains challenging due to pronounced information loss and…
Recent years have witnessed the dramatic growth of Internet video traffic, where the video bitstreams are often compressed and delivered in low quality to fit the streamer's uplink bandwidth. To alleviate the quality degradation, it comes…
Token-based video representation has emerged as a promising approach for enabling large language models (LLMs) to interpret video content. However, existing token reduction techniques, such as pruning and merging, often disrupt essential…
Despite the advancements in cutting-edge technologies, audio signal processing continues to pose challenges and lacks the precision of a human speech processing system. To address these challenges, we propose a novel approach to simplify…
Efficient compression of language model weights is increasingly critical as model scale and deployment grow. Yet, most existing methods rely on handcrafted transforms and heuristics, reflecting the limited understanding of weights as a data…
We study the segmental recurrent neural network for end-to-end acoustic modelling. This model connects the segmental conditional random field (CRF) with a recurrent neural network (RNN) used for feature extraction. Compared to most previous…
We propose and evaluate new techniques for compressing and speeding up dense matrix multiplications as found in the fully connected and recurrent layers of neural networks for embedded large vocabulary continuous speech recognition (LVCSR).…
Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video…
Neural audio codecs are initially introduced to compress audio data into compact codes to reduce transmission latency. Researchers recently discovered the potential of codecs as suitable tokenizers for converting continuous audio into…
Neural video compression (NVC) technologies have advanced rapidly in recent years, yielding state-of-the-art schemes such as DCVC-RT that offer superior compression efficiency to H.266/VVC and real-time encoding/decoding capabilities.…
Language models have been successfully used to model natural signals, such as images, speech, and music. A key component of these models is a high quality neural compression model that can compress high-dimensional natural signals into…
Multimodal Large Language Models (MLLMs) have revolutionized video understanding, yet are still limited by context length when processing long videos. Recent methods compress videos by leveraging visual redundancy uniformly, yielding…
The vast majority of natural sensory data is temporally redundant. Video frames or audio samples which are sampled at nearby points in time tend to have similar values. Typically, deep learning algorithms take no advantage of this…
Recent progress in audio source separation lead by deep learning has enabled many neural network models to provide robust solutions to this fundamental estimation problem. In this study, we provide a family of efficient neural network…
Model compression, such as pruning and quantization, has been widely applied to optimize neural networks on resource-limited classical devices. Recently, there are growing interest in variational quantum circuits (VQC), that is, a type of…
High-quality speech coding at low bitrates is crucial for bandwidth-constrained applications, yet remains challenging due to the severe loss of quality-critical information in highly compressed representations. To overcome this challenge,…
The neural transducer is an end-to-end model for automatic speech recognition (ASR). While the model is well-suited for streaming ASR, the training process remains challenging. During training, the memory requirements may quickly exceed the…