Related papers: Collapsed speech segment detection and suppression…

In this paper, we propose the FeatherWave, yet another variant of WaveRNN vocoder combining the multi-band signal processing and the linear predictive coding. The LPCNet, a recently proposed neural vocoder which utilized the linear…

This paper presents a novel neural vocoder named APNet which reconstructs speech waveforms from acoustic features by predicting amplitude and phase spectra directly. The APNet vocoder is composed of an amplitude spectrum predictor (ASP) and…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…

This research presents a novel approach to enhancing automatic speech recognition systems by integrating noise detection capabilities directly into the recognition architecture. Building upon the wav2vec2 framework, the proposed method…

Noise suppression (NS) algorithms are effective in improving speech quality in many cases. However, aggressive noise suppression can damage the target speech, reducing both speech intelligibility and quality despite removing the noise. This…

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…

Masked language models have revolutionized natural language processing systems in the past few years. A recently introduced generalization of masked language models called warped language models are trained to be more robust to the types of…

Recent audio generation models typically rely on Variational Autoencoders (VAEs) and perform generation within the VAE latent space. Although VAEs excel at compression and reconstruction, their latents inherently encode low-level acoustic…

Since the introduction of Generative Adversarial Networks (GANs) in speech synthesis, remarkable achievements have been attained. In a thorough exploration of vocoders, it has been discovered that audio waveforms can be generated at speeds…

Thanks to advancements in deep learning, speech generation systems now power a variety of real-world applications, such as text-to-speech for individuals with speech disorders, voice chatbots in call centers, cross-linguistic speech…

In this work, we present CleanUNet, a causal speech denoising model on the raw waveform. The proposed model is based on an encoder-decoder architecture combined with several self-attention blocks to refine its bottleneck representations,…

State-of-the-art statistical parametric speech synthesis (SPSS) generally uses a vocoder to represent speech signals and parameterize them into features for subsequent modeling. Magnitude spectrum has been a dominant feature over the years.…

Most neural vocoders employ band-limited mel-spectrograms to generate waveforms. If full-band spectral features are used as the input, the vocoder can be provided with as much acoustic information as possible. However, in some models…

Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and…

Neural audio codecs, used as speech tokenizers, have demonstrated remarkable potential in the field of speech generation. However, to ensure high-fidelity audio reconstruction, neural audio codecs typically encode audio into long sequences…

Generating sound effects that humans want is an important topic. However, there are few studies in this area for sound generation. In this study, we investigate generating sound conditioned on a text prompt and propose a novel text-to-sound…

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015…

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…

Robust speech processing in multi-talker environments requires effective speech separation. Recent deep learning systems have made significant progress toward solving this problem, yet it remains challenging particularly in real-time, short…

Traditional low bit-rate speech coding approach only handles narrowband speech at 8kHz, which limits further improvements in speech quality. Motivated by recent successful exploration of deep learning methods for image and speech…