Related papers: Rate-Aware Learned Speech Compression
Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. In this paper, we propose a multi-modal DSR model by leveraging neural…
Recently, encoder-decoder neural networks have shown impressive performance on many sequence-related tasks. The architecture commonly uses an attentional mechanism which allows the model to learn alignments between the source and the target…
The entropy bottleneck introduced by Ball\'e et al. is a common component used in many learned compression models. It encodes a transformed latent representation using a static distribution whose parameters are learned during training.…
Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or…
Video encoders optimize compression for human perception by minimizing reconstruction error under bit-rate constraints. In many modern applications such as autonomous driving, an overwhelming majority of videos serve as input for AI systems…
We address the problem of efficiently compressing video for conferencing-type applications. We build on recent approaches based on image animation, which can achieve good reconstruction quality at very low bitrate by representing face…
Standardized lossy video coding is at the core of almost all real-world video processing pipelines. Rate control is used to enable standard codecs to adapt to different network bandwidth conditions or storage constraints. However, standard…
Neural image compression has surpassed state-of-the-art traditional codecs (H.266/VVC) for rate-distortion (RD) performance, but suffers from large complexity and separate models for different rate-distortion trade-offs. In this paper, we…
State-of-the-art neural language models represented by Transformers are becoming increasingly complex and expensive for practical applications. Low-bit deep neural network quantization techniques provides a powerful solution to dramatically…
Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…
Recent advancements in speech encoders have drawn attention due to their integration with Large Language Models for various speech tasks. While most research has focused on either causal or full-context speech encoders, there's limited…
Recent advances in implicit neural representation (INR)-based video coding have demonstrated its potential to compete with both conventional and other learning-based approaches. With INR methods, a neural network is trained to overfit a…
We present SoundStream, a novel neural audio codec that can efficiently compress speech, music and general audio at bitrates normally targeted by speech-tailored codecs. SoundStream relies on a model architecture composed by a fully…
Neural receivers have shown outstanding performance compared to the conventional ones but this comes with a high network complexity leading to a heavy computational cost. This poses significant challenges in their deployment on…
Large speech models are rapidly gaining traction in research community. As a result, model compression has become an important topic, so that these models can fit in memory and be served with reduced cost. Practical approaches for…
Neural Audio Codecs (NACs) have become increasingly adopted in speech processing tasks due to their excellent rate-distortion performance and compatibility with Large Language Models (LLMs) as discrete feature representations for audio…
Convolutional layers with 1-D filters are often used as frontend to encode audio signals. Unlike fixed time-frequency representations, they can adapt to the local characteristics of input data. However, 1-D filters on raw audio are hard to…
Despite a short history, neural image codecs have been shown to surpass classical image codecs in terms of rate-distortion performance. However, most of them suffer from significantly longer decoding times, which hinders the practical…
Learning, prediction, and compression are intimately connected: a model that accurately predicts the next symbol in a sequence can be coupled with a source coder to compress that sequence near its information-theoretic limit. When tokenized…
Dysarthric speech reconstruction (DSR) systems aim to automatically convert dysarthric speech into normal-sounding speech. The technology eases communication with speakers affected by the neuromotor disorder and enhances their social…