Related papers: Hierarchical disentangled representation learning …
Self-supervised learning in speech involves training a speech representation network on a large-scale unannotated speech corpus, and then applying the learned representations to downstream tasks. Since the majority of the downstream tasks…
Self-supervised learning (SSL) offers a powerful way to learn robust, generalizable representations without labeled data. In music, where labeled data is scarce, existing SSL methods typically use generated supervision and multi-view…
Deep learning-based works for singing voice separation have performed exceptionally well in the recent past. However, most of these works do not focus on allowing users to interact with the model to improve performance. This can be crucial…
Singing voice synthesis (SVS) is a task that aims to generate audio signals according to musical scores and lyrics. With its multifaceted nature concerning music and language, producing singing voices indistinguishable from that of human…
We propose an unsupervised learning method to disentangle speech into content representation and speaker identity representation. We apply this method to the challenging one-shot cross-lingual voice conversion task to demonstrate the…
Many existing works on voice conversion (VC) tasks use automatic speech recognition (ASR) models for ensuring linguistic consistency between source and converted samples. However, for the low-data resource domains, training a high-quality…
Voice style transfer, also called voice conversion, seeks to modify one speaker's voice to generate speech as if it came from another (target) speaker. Previous works have made progress on voice conversion with parallel training data and…
Voice Conversion (VC) converts the voice of a source speech to that of a target while maintaining the source's content. Speech can be mainly decomposed into four components: content, timbre, rhythm and pitch. Unfortunately, most related…
In this work we present a method for unsupervised learning of audio representations, focused on the task of singing voice separation. We build upon a previously proposed method for learning representations of time-domain music signals with…
Voice conversion (VC) modifies voice characteristics while preserving linguistic content. This paper presents the Stepback network, a novel model for converting speaker identity using non-parallel data. Unlike traditional VC methods that…
Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…
Traditional studies on voice conversion (VC) have made progress with parallel training data and known speakers. Good voice conversion quality is obtained by exploring better alignment modules or expressive mapping functions. In this study,…
In real-world singing voice conversion (SVC) applications, environmental noise and the demand for expressive output pose significant challenges. Conventional methods, however, are typically designed without accounting for real deployment…
Deep representation learning offers a powerful paradigm for mapping input data onto an organized embedding space and is useful for many music information retrieval tasks. Two central methods for representation learning include deep metric…
Voice conversion is an increasingly popular technology, and the growing number of real-time applications requires models with streaming conversion capabilities. Unlike typical (non-streaming) voice conversion, which can leverage the entire…
Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance. This paper first studies the…
Singing voice correction (SVC) is an appealing application for amateur singers. Commercial products automate SVC by snapping pitch contours to equal-tempered scales, which could lead to deadpan modifications. Together with the neglect of…
Singing voice conversion is to convert the source singing voice into the target singing voice except for the content. Currently, flow-based models can complete the task of voice conversion, but they struggle to effectively extract latent…
The objective of deep learning methods based on encoder-decoder architectures for music source separation is to approximate either ideal time-frequency masks or spectral representations of the target music source(s). The spectral…
This paper presents a method of sequence-to-sequence (seq2seq) voice conversion using non-parallel training data. In this method, disentangled linguistic and speaker representations are extracted from acoustic features, and voice conversion…