Related papers: ELF: Encoding Speaker-Specific Latent Speech Featu…

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…

This paper presents a novel zero-shot learning approach towards personalized speech enhancement through the use of a sparsely active ensemble model. Optimizing speech denoising systems towards a particular test-time speaker can improve…

Current synthetic speech detection (SSD) methods perform well on certain datasets but still face issues of robustness and interpretability. A possible reason is that these methods do not analyze the deficiencies of synthetic speech. In this…

Conventional text-to-speech (TTS) research has predominantly focused on enhancing the quality of synthesized speech for speakers in the training dataset. The challenge of synthesizing lifelike speech for unseen, out-of-dataset speakers,…

We introduce a new automatic evaluation method for speaker similarity assessment, that is consistent with human perceptual scores. Modern neural text-to-speech models require a vast amount of clean training data, which is why many solutions…

We propose a novel framework for electrolaryngeal speech intelligibility enhancement through the use of robust linguistic encoders. Pretraining and fine-tuning approaches have proven to work well in this task, but in most cases, various…

The objective of this paper is to learn representations of speaker identity without access to manually annotated data. To do so, we develop a self-supervised learning objective that exploits the natural cross-modal synchrony between faces…

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…

Singing voice synthesis has been paid rising attention with the rapid development of speech synthesis area. In general, a studio-level singing corpus is usually necessary to produce a natural singing voice from lyrics and music-related…

Traditional speech separation and speaker diarization approaches rely on prior knowledge of target speakers or a predetermined number of participants in audio signals. To address these limitations, recent advances focus on developing…

Speaker anonymization aims to conceal cues to speaker identity while preserving linguistic content. Current machine learning based approaches require substantial computational resources, hindering real-time streaming applications. To…

Speaker recognition systems are often limited to classification tasks and struggle to generate detailed speaker characteristics or provide context-rich descriptions. These models primarily extract embeddings for speaker identification but…

In recent years, the remarkable advancements in deep neural networks have brought tremendous convenience. However, the training process of a highly effective model necessitates a substantial quantity of samples, which brings huge potential…

Several methods have recently been proposed to analyze speech and automatically infer the personality of the speaker. These methods often rely on prosodic and other hand crafted speech processing features extracted with off-the-shelf…

Keyword spotting systems often struggle to generalize to a diverse population with various accents and age groups. To address this challenge, we propose a novel approach that integrates speaker information into keyword spotting using…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

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…

Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong…

Large speech emotion recognition datasets are hard to obtain, and small datasets may contain biases. Deep-net-based classifiers, in turn, are prone to exploit those biases and find shortcuts such as speaker characteristics. These shortcuts…