Related papers: A Robust Frame-based Nonlinear Prediction System f…
This paper presents a new neural speech compression method that is practical in the sense that it operates at low bitrate, introduces a low latency, is compatible in computational complexity with current mobile devices, and provides a…
Polar codes can theoretically achieve very competitive Frame Error Rates. In practice, their performance may depend on the chosen decoding procedure, as well as other parameters of the communication system they are deployed upon. As a…
This paper is dedicated to an efficient compression of weights and optimizer states (called checkpoints) obtained at different stages during a neural network training process. First, we propose a prediction-based compression approach, where…
We propose Kernel Predictive Control (KPC), a learning-based predictive control strategy that enjoys deterministic guarantees of safety. Noise-corrupted samples of the unknown system dynamics are used to learn several models through the…
The quality of speech codecs deteriorates at low bitrates due to high quantization noise. A post-filter is generally employed to enhance the quality of the coded speech. In this paper, a data-driven post-filter relying on masking in the…
Speech compression is commonly used to send voice over radio channels in applications such as mobile telephony and two-way push-to-talk (PTT) radio. In classical systems, the speech codec is combined with forward error correction,…
Recently, Conformer as a backbone network for end-to-end automatic speech recognition achieved state-of-the-art performance. The Conformer block leverages a self-attention mechanism to capture global information, along with a convolutional…
This study propose a fully automated system for speech correction and accent reduction. Consider the application scenario that a recorded speech audio contains certain errors, e.g., inappropriate words, mispronunciations, that need to be…
The design of codes for feedback-enabled communications has been a long-standing open problem. Recent research on non-linear, deep learning-based coding schemes have demonstrated significant improvements in communication reliability over…
A deep neural network (DNN)-based model has been developed to predict non-parametric distributions of durations of phonemes in specified phonetic contexts and used to explore which factors influence durations most. Major factors in US…
Neural speech codecs have gained great attention for their outstanding reconstruction with discrete token representations. It is a crucial component in generative tasks such as speech coding and large language models (LLM). However, most…
In this paper, a novel method of designing a codebook for noise robust speaker identification purpose utilizing Genetic Algorithm has been proposed. Wiener filter has been used to remove the background noises from the source speech…
We propose a neural network model to estimate the current frame from two reference frames, using affine transformation and adaptive spatially-varying filters. The estimated affine transformation allows for using shorter filters compared to…
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,…
Many speech processing tasks involve measuring the acoustic similarity between speech segments. Acoustic word embeddings (AWE) allow for efficient comparisons by mapping speech segments of arbitrary duration to fixed-dimensional vectors.…
We present a novel neural encoder system for acoustic-to-articulatory inversion. We leverage the Pink Trombone voice synthesizer that reveals articulatory parameters (e.g tongue position and vocal cord configuration). Our system is designed…
Multi-frame algorithms for single-channel speech enhancement are able to take advantage from short-time correlations within the speech signal. Deep Filtering (DF) was proposed to directly estimate a complex filter in frequency domain to…
Neural speech codecs have been widely used in audio compression and various downstream tasks. Current mainstream codecs are fixed-frame-rate (FFR), which allocate the same number of tokens to every equal-duration slice. However, speech is…
In this paper, we propose a novel neural network model called RNN Encoder-Decoder that consists of two recurrent neural networks (RNN). One RNN encodes a sequence of symbols into a fixed-length vector representation, and the other decodes…
Context-aware compression techniques have gained increasing attention as model sizes continue to grow, introducing computational bottlenecks that hinder efficient deployment. A structured encoding approach was proposed to selectively…