相关论文: Rhythm Modeling for Voice Conversion

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

Voice Conversion(VC) refers to changing the timbre of a speech while retaining the discourse content. Recently, many works have focused on disentangle-based learning techniques to separate the timbre and the linguistic content information…

The goal of this work is to train discriminative cross-modal embeddings without access to manually annotated data. Recent advances in self-supervised learning have shown that effective representations can be learnt from natural cross-modal…

We propose RemixIT, a simple and novel self-supervised training method for speech enhancement. The proposed method is based on a continuously self-training scheme that overcomes limitations from previous studies including assumptions for…

Subword modeling for zero-resource languages aims to learn low-level representations of speech audio without using transcriptions or other resources from the target language (such as text corpora or pronunciation dictionaries). A good…

A singing voice conversion model converts a song in the voice of an arbitrary source singer to the voice of a target singer. Recently, methods that leverage self-supervised audio representations such as HuBERT and Wav2Vec 2.0 have helped…

Voice conversion is a task to convert a non-linguistic feature of a given utterance. Since naturalness of speech strongly depends on its pitch pattern, in some applications, it would be desirable to keep the original rise/fall pitch pattern…

Emotional voice conversion aims to convert the spectrum and prosody to change the emotional patterns of speech, while preserving the speaker identity and linguistic content. Many studies require parallel speech data between different…

In the context of environmental sound classification, the adaptability of systems is key: which sound classes are interesting depends on the context and the user's needs. Recent advances in text-to-audio retrieval allow for zero-shot audio…

We propose an algorithm that is capable of synthesizing high quality target speaker's singing voice given only their normal speech samples. The proposed algorithm first integrate speech and singing synthesis into a unified framework, and…

Non-parallel voice conversion (VC) is typically achieved using lossy representations of the source speech. However, ensuring only speaker identity information is dropped whilst all other information from the source speech is retained is a…

Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping. In this paper, we…

In voice conversion (VC) applications, diffusion and flow-matching models have exhibited exceptional speech quality and speaker similarity performances. However, they are limited by slow conversion owing to their iterative inference.…

Melody preservation is crucial in singing voice conversion (SVC). However, in many scenarios, audio is often accompanied with background music (BGM), which can cause audio distortion and interfere with the extraction of melody and other key…

Prosody transfer is well-studied in the context of expressive speech synthesis. Cross-lingual prosody transfer, however, is challenging and has been under-explored to date. In this paper, we present a novel solution to learn prosody…

Here we present a novel approach to conditioning the SampleRNN generative model for voice conversion (VC). Conventional methods for VC modify the perceived speaker identity by converting between source and target acoustic features. Our…

Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately,…

In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a…

One-shot style transfer is a challenging task, since training on one utterance makes model extremely easy to over-fit to training data and causes low speaker similarity and lack of expressiveness. In this paper, we build on the…