Related papers: Wavehax: Aliasing-Free Neural Waveform Synthesis B…
Encoding more information into wave fields is a central goal in imaging, communication, and wave control. Optical holography benefits from polarization multiplexing, but acoustic holography remains largely limited to pressure-only encoding…
Building a voice conversion system for noisy target speakers, such as users providing noisy samples or Internet found data, is a challenging task since the use of contaminated speech in model training will apparently degrade the conversion…
This paper addresses the challenge of enhancing the realism of vocoder-generated singing voice audio by mitigating the distinguishable disparities between synthetic and real-life recordings, particularly in high-frequency spectrogram…
Neural networks have become ubiquitous with guitar distortion effects modelling in recent years. Despite their ability to yield perceptually convincing models, they are susceptible to frequency aliasing when driven by high frequency and…
Autoregressive neural vocoders have achieved outstanding performance in speech synthesis tasks such as text-to-speech and voice conversion. An autoregressive vocoder predicts a sample at some time step conditioned on those at previous time…
Custom voice is to construct a personal speech synthesis system by adapting the source speech synthesis model to the target model through the target few recordings. The solution to constructing a custom voice is to combine an adaptive…
Recent advances in image generation, particularly via diffusion models, have led to impressive improvements in image synthesis quality. Despite this, diffusion models are still challenged by model-induced artifacts and limited stability in…
Generating full-length, high-quality songs is challenging, as it requires maintaining long-term coherence both across text and music modalities and within the music modality itself. Existing non-autoregressive (NAR) frameworks, while…
Unsupervised representation learning of speech has been of keen interest in recent years, which is for example evident in the wide interest of the ZeroSpeech challenges. This work presents a new method for learning frame level…
Neural Audio Codecs, initially designed as a compression technique, have gained more attention recently for speech generation. Codec models represent each audio frame as a sequence of tokens, i.e., discrete embeddings. The discrete and…
Transformer-based audio self-supervised learning (SSL) models commonly use spectrograms, vision-style Transformers, and masked modeling objectives. However, convolutional patchification with temporal downsampling lowers the effective…
Recent neural networks such as WaveNet and sampleRNN that learn directly from speech waveform samples have achieved very high-quality synthetic speech in terms of both naturalness and speaker similarity even in multi-speaker text-to-speech…
Neural audio codecs have revolutionized audio processing by enabling speech tasks to be performed on highly compressed representations. Recent work has shown that speech separation can be achieved within these compressed domains, offering…
Recently, denoising diffusion models have demonstrated remarkable performance among generative models in various domains. However, in the speech domain, the application of diffusion models for synthesizing time-varying audio faces…
Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas…
This paper proposes voicing-aware conditional discriminators for Parallel WaveGAN-based waveform synthesis systems. In this framework, we adopt a projection-based conditioning method that can significantly improve the discriminator's…
We propose Hierarchical Audio Codec (HAC), a unified neural speech codec that factorizes its bottleneck into three linguistic levels-acoustic, phonetic, and lexical-within a single model. HAC leverages two knowledge distillation objectives:…
A method for the design of Fast Haar wavelet for signal processing and image processing has been proposed. In the proposed work, the analysis bank and synthesis bank of Haar wavelet is modified by using polyphase structure. Finally, the…
AI-synthesized voice technology has the potential to create realistic human voices for beneficial applications, but it can also be misused for malicious purposes. While existing AI-synthesized voice detection models excel in intra-domain…
Existing dominant methods for audio generation include Generative Adversarial Networks (GANs) and diffusion-based methods like Flow Matching. GANs suffer from slow convergence during training, while diffusion methods require multi-step…