Related papers: pch2csd: an application for converting Nord Modula…
In this paper, we distinguish two guessing algorithms for decoding binary linear codes. One is the guessing noise decoding (GND) algorithm, and the other is the guessing codeword decoding (GCD) algorithm. We prove that the GCD is a maximum…
We present a unified system to realize one-shot voice conversion (VC) on the pitch, rhythm, and speaker attributes. Existing works generally ignore the correlation between prosody and language content, leading to the degradation of…
Text-to-Speech (TTS) services that run on edge devices have many advantages compared to cloud TTS, e.g., latency and privacy issues. However, neural vocoders with a low complexity and small model footprint inevitably generate annoying…
Two-part reconstruction is a framework for signal recovery in compressed sensing (CS), in which the advantages of two different algorithms are combined. Our framework allows to accelerate the reconstruction procedure without compromising…
Although power line communication (PLC) systems are available everywhere, unfortunately these systems are not suitable for information transmission due to the effects of the impulsive noise. Therefore, many previous studies on channel codes…
This paper introduces Claycode, a novel 2D scannable code designed for extensive stylization and deformation. Unlike traditional matrix-based codes (e.g., QR codes), Claycodes encode their message in a tree structure. During the encoding…
Inspired by recent research, we explore ways to model the highly morphological Finnish language at the level of characters while maintaining the performance of word-level models. We propose a new Character-to-Word-to-Character (C2W2C)…
To operate in real-world high-stakes environments, deep learning systems have to endure noises that have been continuously thwarting their robustness. Data-end defense, which improves robustness by operations on input data instead of…
While many current neural speech codecs achieve impressive reconstructed speech quality, they often neglect latency and complexity considerations, limiting their practical deployment in downstream tasks such as real-time speech…
Despite great success in many applications, deep neural networks are not always robust in practice. For instance, a convolutional neuron network (CNN) model for classification tasks often performs unsatisfactorily in classifying some…
Neural audio codecs have been widely adopted in audio-generative tasks because their compact and discrete representations are suitable for both large-language-model-style and regression-based generative models. However, most neural codecs…
Neural networks have proven to be a formidable tool to tackle the problem of speech coding at very low bit rates. However, the design of a neural coder that can be operated robustly under real-world conditions remains a major challenge.…
This paper presents fairseq S^2, a fairseq extension for speech synthesis. We implement a number of autoregressive (AR) and non-AR text-to-speech models, and their multi-speaker variants. To enable training speech synthesis models with less…
The Locust simulation package is a new C++ software tool developed to simulate the measurement of time-varying electromagnetic fields using RF detection techniques. Modularity and flexibility allow for arbitrary input signals, while…
Inspired by modular software design principles of independence, interchangeability, and clarity of interface, we introduce a method for enforcing encoder-decoder modularity in seq2seq models without sacrificing the overall model quality or…
Neural speech codecs have revolutionized speech coding, achieving higher compression while preserving audio fidelity. Beyond compression, they have emerged as tokenization strategies, enabling language modeling on speech and driving…
Neural audio synthesis methods now allow specifying ideas in natural language. However, these methods produce results that cannot be easily tweaked, as they are based on large latent spaces and up to billions of uninterpretable parameters.…
Neural speech synthesis models can synthesize high quality speech but typically require a high computational complexity to do so. In previous work, we introduced LPCNet, which uses linear prediction to significantly reduce the complexity of…
Polar codes have emerged as the most favorable channel codes for their unique capacity-achieving property. To date, numerous works have been reported for efficient design of polar codes decoder. However, these prior efforts focused on…
Vocoders received renewed attention as main components in statistical parametric text-to-speech (TTS) synthesis and speech transformation systems. Even though there are vocoding techniques give almost accepted synthesized speech, their high…