Related papers: Sequence-to-sequence Singing Voice Synthesis with …
Recent Text-to-Speech (TTS) systems trained on reading or acted corpora have achieved near human-level naturalness. The diversity of human speech, however, often goes beyond the coverage of these corpora. We believe the ability to handle…
Modern speaker verification systems primarily rely on speaker embeddings, followed by verification based on cosine similarity between the embedding vectors of the enrollment and test utterances. While effective, these methods struggle with…
We present several methods to improve the generalisation of language identification (LID) systems to new speakers and to new domains. These methods involve Spectral augmentation, where spectrograms are masked in the frequency or time bands…
Recent speech enhancement (SE) models increasingly leverage self-supervised learning (SSL) representations for their rich semantic information. Typically, intermediate features are aggregated into a single representation via a lightweight…
Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…
Personalized speech enhancement (PSE) has shown convincing results when it comes to extracting a known target voice among interfering ones. The corresponding systems usually incorporate a representation of the target voice within the…
In this work, we present an end-to-end binaural speech synthesis system that combines a low-bitrate audio codec with a powerful binaural decoder that is capable of accurate speech binauralization while faithfully reconstructing…
End-to-end (E2E) automatic speech recognition (ASR) models have recently demonstrated superior performance over the traditional hybrid ASR models. Training an E2E ASR model requires a large amount of data which is not only expensive but may…
Single-channel speech enhancement approaches do not always improve automatic recognition rates in the presence of noise, because they can introduce distortions unhelpful for recognition. Following a trend towards end-to-end training of…
The lack of a publicly-available large-scale and diverse dataset has long been a significant bottleneck for singing voice applications like Singing Voice Synthesis (SVS) and Singing Voice Conversion (SVC). To tackle this problem, we present…
With just a few speech samples, it is possible to perfectly replicate a speaker's voice in recent years, while malicious voice exploitation (e.g., telecom fraud for illegal financial gain) has brought huge hazards in our daily lives.…
Incremental improvements in accuracy of Convolutional Neural Networks are usually achieved through use of deeper and more complex models trained on larger datasets. However, enlarging dataset and models increases the computation and storage…
High-quality singing annotations are fundamental to modern Singing Voice Synthesis (SVS) systems. However, obtaining these annotations at scale through manual labeling is unrealistic due to the substantial labor and musical expertise…
Modern text-to-speech synthesis pipelines typically involve multiple processing stages, each of which is designed or learnt independently from the rest. In this work, we take on the challenging task of learning to synthesise speech from…
Deep generative models have achieved significant progress in speech synthesis to date, while high-fidelity singing voice synthesis is still an open problem for its long continuous pronunciation, rich high-frequency parts, and strong…
Because videos in the wild can be out of sync for various reasons, a sync-net is used to bring the video back into sync for tasks that require synchronized videos. Previous state-of-the-art (SOTA) sync-nets use InfoNCE loss, rely on the…
Labeling a training set is often expensive and susceptible to errors, making the design of robust loss functions for label noise an important problem. The symmetry condition provides theoretical guarantees for robustness to such noise. In…
End-to-end models are an attractive new approach to spoken language understanding (SLU) in which the meaning of an utterance is inferred directly from the raw audio without employing the standard pipeline composed of a separately trained…
We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre.…
Speaker adaptation methods aim to create fair quality synthesis speech voice font for target speakers while only limited resources available. Recently, as deep neural networks based statistical parametric speech synthesis (SPSS) methods…