Related papers: Learning Expressive Disentangled Speech Representa…
Expressive zero-shot voice conversion (VC) is a critical and challenging task that aims to transform the source timbre into an arbitrary unseen speaker while preserving the original content and expressive qualities. Despite recent progress…
We propose a method for learning de-identified prosody representations from raw audio using a contrastive self-supervised signal. Whereas prior work has relied on conditioning models on bottlenecks, we introduce a set of inductive biases…
The goal of accent conversion (AC) is to convert speech accents while preserving content and speaker identity. Previous methods either required reference utterances during inference, did not preserve speaker identity well, or used…
While existing speech audio codecs designed for compression exploit limited forms of temporal redundancy and allow for multi-scale representations, they tend to represent all features of audio in the same way. In contrast, generative voice…
While signal conversion and disentangled representation learning have shown promise for manipulating data attributes across domains such as audio, image, and multimodal generation, existing approaches, especially for speech style…
This paper proposes RefXVC, a method for cross-lingual voice conversion (XVC) that leverages reference information to improve conversion performance. Previous XVC works generally take an average speaker embedding to condition the speaker…
Voice conversion has gained increasing popularity within the field of audio manipulation and speech synthesis. Often, the main objective is to transfer the input identity to that of a target speaker without changing its linguistic content.…
An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…
This paper presents an end-to-end high-quality singing voice synthesis (SVS) system that uses bidirectional encoder representation from Transformers (BERT) derived semantic embeddings to improve the expressiveness of the synthesized singing…
Speech time reversal refers to the process of reversing the entire speech signal in time, causing it to play backward. Such signals are completely unintelligible since the fundamental structures of phonemes and syllables are destroyed.…
Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…
We propose a learnable content adaptive front end for audio signal processing. Before the modern advent of deep learning, we used fixed representation non-learnable front-ends like spectrogram or mel-spectrogram with/without neural…
We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms. The goal is to learn a representation able to capture high level semantic content…
Emotional voice conversion (EVC) aims to change the emotional state of an utterance while preserving the linguistic content and speaker identity. In this paper, we propose a novel 2-stage training strategy for sequence-to-sequence emotional…
Expressive speech synthesis, like audiobook synthesis, is still challenging for style representation learning and prediction. Deriving from reference audio or predicting style tags from text requires a huge amount of labeled data, which is…
Speaker anonymization seeks to conceal a speaker's identity while preserving the utility of their speech. The achieved privacy is commonly evaluated with a speaker recognition model trained on anonymized speech. Although this represents a…
Self-supervised learning (SSL) is a powerful tool that allows learning of underlying representations from unlabeled data. Transformer based models such as wav2vec 2.0 and HuBERT are leading the field in the speech domain. Generally these…
One-shot voice conversion (VC) aims to convert speech from any source speaker to an arbitrary target speaker with only a few seconds of reference speech from the target speaker. This relies heavily on disentangling the speaker's identity…
The representation learning of speech, without textual resources, is an area of significant interest for many low resource speech applications. In this paper, we describe an approach to self-supervised representation learning from raw audio…
Voice conversion is a task of synthesizing an utterance with target speaker's voice while maintaining linguistic information of the source utterance. While a speaker can produce varying utterances from a single script with different…