Related papers: A Full Frequency Masking Vocoder for Legal Eavesdr…

We introduce a new beam search decoder that is fully differentiable, making it possible to optimize at training time through the inference procedure. Our decoder allows us to combine models which operate at different granularities (e.g.…

Identifying multiple speakers without knowing where a speaker's voice is in a recording is a challenging task. This paper proposes a hierarchical network with transformer encoders and memory mechanism to address this problem. The proposed…

Transient loud intrusions, often occurring in noisy environments, can completely overpower speech signal and lead to an inevitable loss of information. While existing algorithms for noise suppression can yield impressive results, their…

New security and privacy concerns arise due to the growing popularity of voice assistant (VA) deployments in home and enterprise networks. A number of past research results have demonstrated how malicious actors can use hidden commands to…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

This paper proposes a WaveNet-based neural excitation model (ExcitNet) for statistical parametric speech synthesis systems. Conventional WaveNet-based neural vocoding systems significantly improve the perceptual quality of synthesized…

With the fast development of natural language processing, recent advances in information hiding focus on covertly embedding secret information into texts. These algorithms either modify a given cover text or directly generate a text…

This work studies the use of attention masking in transformer transducer based speech recognition for building a single configurable model for different deployment scenarios. We present a comprehensive set of experiments comparing fixed…

Automated audio captioning aims to use natural language to describe the content of audio data. This paper presents an audio captioning system with an encoder-decoder architecture, where the decoder predicts words based on audio features…

It is shown how a recently proposed method of cloaking is effective over a broad range of frequencies. The method is based on three or more active devices. The devices, while not radiating significantly, create a ``quiet zone'' between the…

Recent advancements in neural vocoding are predominantly driven by Generative Adversarial Networks (GANs) operating in the time-domain. While effective, this approach neglects the inductive bias offered by time-frequency representations,…

This paper proposes a novel neural denoising vocoder that can generate clean speech waveforms from noisy mel-spectrograms. The proposed neural denoising vocoder consists of two components, i.e., a spectrum predictor and a enhancement…

A survey of acoustic devices for focusing airborne sound is presented. We introduce a new approach to design high quality acoustic lenses based on arrays of cylindrical rigid scatterers in air. A population based stochastic search algorithm…

Hiding messages for countless security purposes has become a highly fascinating subject nowadays. Encryption facilitates the data hiding. With the express development of technology, people tend to figure out a method capable of hiding a…

Automated audio captioning is machine listening task whose goal is to describe an audio using free text. An automated audio captioning system has to be implemented as it accepts an audio as input and outputs as textual description, that is,…

Data hiding is essential for secure communication across digital media, and recent advances in Deep Neural Networks (DNNs) provide enhanced methods for embedding secret information effectively. However, previous audio hiding methods often…

State-of-the-art text-independent speaker verification systems typically use cepstral features or filter bank energies as speech features. Recent studies attempted to extract speaker embeddings directly from raw waveforms and have shown…

Uncertainty modeling in speaker representation aims to learn the variability present in speech utterances. While the conventional cosine-scoring is computationally efficient and prevalent in speaker recognition, it lacks the capability to…

Voiceprints are widely used for authentication; however, they are easily captured in public settings and cannot be revoked once leaked. Existing anonymization systems operate inside recording devices, which makes them ineffective when…

We study the problem of remote state estimation, in the presence of an eavesdropper. An authorized user estimates the state of a linear plant, based on the data received from a sensor, while the data may also be intercepted by the…