相关论文: Towards Robust Neural Vocoding for Speech Generati…

Neural vocoders are central to speech synthesis; despite their success, most still suffer from limited prosody modeling and inaccurate phase reconstruction. We propose a vocoder that introduces prosody-guided harmonic attention to enhance…

Speaker recognition systems based on deep speaker embeddings have achieved significant performance in controlled conditions according to the results obtained for early NIST SRE (Speaker Recognition Evaluation) datasets. From the practical…

We describe a sequence-to-sequence neural network which directly generates speech waveforms from text inputs. The architecture extends the Tacotron model by incorporating a normalizing flow into the autoregressive decoder loop. Output…

While speaker adaptation for end-to-end speech synthesis using speaker embeddings can produce good speaker similarity for speakers seen during training, there remains a gap for zero-shot adaptation to unseen speakers. We investigate…

Perceptual voice quality assessment plays a vital role in diagnosing and monitoring voice disorders. Traditional methods, such as the Consensus Auditory-Perceptual Evaluation of Voice (CAPE-V) and the Grade, Roughness, Breathiness,…

Entertainment-oriented singing voice synthesis (SVS) requires a vocoder to generate high-fidelity (e.g. 48kHz) audio. However, most text-to-speech (TTS) vocoders cannot reconstruct the waveform well in this scenario. In this paper, we…

We explore why deep convolutional neural networks (CNNs) with small two-dimensional kernels, primarily used for modeling spatial relations in images, are also effective in speech recognition. We analyze the representations learned by deep…

We propose noise-robust voice conversion (VC) which takes into account the recording quality and environment of noisy source speech. Conventional denoising training improves the noise robustness of a VC model by learning noisy-to-clean VC…

Voice cloning is a highly desired feature for personalized speech interfaces. Neural network based speech synthesis has been shown to generate high quality speech for a large number of speakers. In this paper, we introduce a neural voice…

Sequence-to-sequence models have been widely used in end-to-end speech processing, for example, automatic speech recognition (ASR), speech translation (ST), and text-to-speech (TTS). This paper focuses on an emergent sequence-to-sequence…

In this paper, we explore vector quantization for acoustic unit discovery. Leveraging unlabelled data, we aim to learn discrete representations of speech that separate phonetic content from speaker-specific details. We propose two neural…

Joint visual and language modeling on large-scale datasets has recently shown good progress in multi-modal tasks when compared to single modal learning. However, robustness of these approaches against real-world perturbations has not been…

Neural network applications generally benefit from larger-sized models, but for current speech enhancement models, larger scale networks often suffer from decreased robustness to the variety of real-world use cases beyond what is…

With the rapid development of neural network architectures and speech processing models, singing voice synthesis with neural networks is becoming the cutting-edge technique of digital music production. In this work, in order to explore how…

Natural and artificial audition can in principle acquire different solutions to a given problem. The constraints of the task, however, can nudge the cognitive science and engineering of audition to qualitatively converge, suggesting that a…

It is desirable for a text-to-speech system to take into account the environment where synthetic speech is presented, and provide appropriate context-dependent output to the user. In this paper, we present and compare various approaches for…

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.…

In recent years, using raw waveforms as input for deep networks has been widely explored for the speaker verification system. For example, RawNet and RawNet2 extracted speaker's feature embeddings from waveforms automatically for…

Recent advancement in Generative Adversarial Networks in speech synthesis domain[3],[2] have shown, that it's possible to train GANs [8] in a reliable manner for high quality coherent waveform generation from mel-spectograms. We propose…

We propose a novel text-to-speech (TTS) framework centered around a neural transducer. Our approach divides the whole TTS pipeline into semantic-level sequence-to-sequence (seq2seq) modeling and fine-grained acoustic modeling stages,…