Related papers: A Full Frequency Masking Vocoder for Legal Eavesdr…
In this paper, we propose an online speaker adaptation method for WaveNet-based neural vocoders in order to improve their performance on speaker-independent waveform generation. In this method, a speaker encoder is first constructed using a…
In this work, we propose a speaker anonymization pipeline that leverages high quality automatic speech recognition and synthesis systems to generate speech conditioned on phonetic transcriptions and anonymized speaker embeddings. Using…
Speaker embeddings are widely used in speaker verification systems and other applications where it is useful to characterise the voice of a speaker with a fixed-length vector. These embeddings tend to be treated as "black box" encodings,…
While universal vocoders have achieved proficient waveform generation across diverse voices, their integration into text-to-speech (TTS) tasks often results in degraded synthetic quality. To address this challenge, we present a novel…
Recent research has delved into speech enhancement (SE) approaches that leverage audio embeddings from pre-trained models, diverging from time-frequency masking or signal prediction techniques. This paper introduces an efficient and…
In the field of deepfake detection, previous studies focus on using reconstruction or mask and prediction methods to train pre-trained models, which are then transferred to fake audio detection training where the encoder is used to extract…
In speaker anonymization, speech recordings are modified in a way that the identity of the speaker remains hidden. While this technology could help to protect the privacy of individuals around the globe, current research restricts this by…
This work investigates the possibility of using non-orthogonal multi-carrier waveforms to defend against eavesdropping attacks. The sophisticated detection required for non-orthogonal signals provides a natural defence mechanism in secure…
Recently, opportunities to transmit speech data to deep learning models executed in the cloud have increased. This has led to growing concerns about speech privacy, including both speaker-specific information and the linguistic content of…
In this paper, we consider the use of artificial noise for secure communications. We propose the notion of practical secrecy as a new design criterion based on the behavior of the eavesdropper's error probability $P_E$, as the…
Voice trigger detection is an important task, which enables activating a voice assistant when a target user speaks a keyword phrase. A detector is typically trained on speech data independent of speaker information and used for the voice…
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding…
Complex-valued processing has brought deep learning-based speech enhancement and signal extraction to a new level. Typically, the process is based on a time-frequency (TF) mask which is applied to a noisy spectrogram, while complex masks…
The reverberation time is one of the most important parameters used to characterize the acoustic property of an enclosure. In real-world scenarios, it is much more convenient to estimate the reverberation time blindly from recorded speech…
It has been found that the signal can be encoded in the choice of the measurement basis of one of the communicating parties, while the outcomes of the measurement are irrelevant for the communication and therefore may be discarded. The…
Speaker anonymization aims to suppress speaker individuality to protect privacy in speech while preserving the other aspects, such as speech content. One effective solution for anonymization is to modify the McAdams coefficient. In this…
Voice conversion (VC) aims to modify the speaker's identity while preserving the linguistic content. Commonly, VC methods use an encoder-decoder architecture, where disentangling the speaker's identity from linguistic information is…
Deep generative models can generate high-fidelity audio conditioned on various types of representations (e.g., mel-spectrograms, Mel-frequency Cepstral Coefficients (MFCC)). Recently, such models have been used to synthesize audio waveforms…
Voice conversion for speaker anonymization is an emerging concept for privacy protection. In a deep learning setting, this is achieved by extracting multiple features from speech, altering the speaker identity, and waveform synthesis.…
The analysis of conversations recorded in everyday life requires privacy protection. In this contribution, we explore a privacy-preserving feature extraction method based on input feature dimension reduction, spectral smoothing and the…