Related papers: Towards Identity Preserving Normal to Dysarthric V…

Dysarthria is a speech disorder characterized by impaired intelligibility and reduced communicative effectiveness. Automatic dysarthria assessment provides a scalable, cost-effective approach for supporting the diagnosis and treatment of…

Dysarthric speech severity assessment typically requires trained clinicians or supervised models built from labelled pathological speech, limiting scalability across languages and clinical settings. We present a training-free method that…

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…

We propose a novel training scheme to optimize voice conversion network with a speaker identity loss function. The training scheme not only minimizes frame-level spectral loss, but also speaker identity loss. We introduce a cycle…

Current research in speech-to-speech translation (S2ST) primarily concentrates on translation accuracy and speech naturalness, often overlooking key elements like paralinguistic information, which is essential for conveying emotions and…

This paper proposes a new task called spatial voice conversion, which aims to convert a target voice while preserving spatial information and non-target signals. Traditional voice conversion methods focus on single-channel waveforms,…

This paper introduces a cross-lingual dubbing system that translates speech from one language to another while preserving key characteristics such as duration, speaker identity, and speaking speed. Despite the strong translation quality of…

Voice conversion (VC) techniques aim to modify speaker identity of an utterance while preserving the underlying linguistic information. Most VC approaches ignore modeling of the speaking style (e.g. emotion and emphasis), which may contain…

We address the problem of cross-speaker style transfer for text-to-speech (TTS) using data augmentation via voice conversion. We assume to have a corpus of neutral non-expressive data from a target speaker and supporting conversational…

Voice conversion (VC) and text-to-speech (TTS) are two tasks that share a similar objective, generating speech with a target voice. However, they are usually developed independently under vastly different frameworks. In this paper, we…

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…

We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that…

Wearable silent speech systems hold significant potential for restoring communication in patients with speech impairments. However, seamless, coherent speech remains elusive, and clinical efficacy is still unproven. Here, we present an…

Dysarthric speech severity classification is crucial for objective clinical assessment and progress monitoring in individuals with motor speech disorders. Although prior methods have addressed this task, achieving robust generalization in…

We present a case study on developing a customized speech-to-text system for a Hungarian speaker with severe dysarthria. State-of-the-art automatic speech recognition (ASR) models struggle with zero-shot transcription of dysarthric speech,…

This paper presents a method for end-to-end cross-lingual text-to-speech (TTS) which aims to preserve the target language's pronunciation regardless of the original speaker's language. The model used is based on a non-attentive Tacotron…

In this paper, we introduce a zero-shot Voice Transfer (VT) module that can be seamlessly integrated into a multi-lingual Text-to-speech (TTS) system to transfer an individual's voice across languages. Our proposed VT module comprises a…

Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target…

Disordered speech recognition is a highly challenging task. The underlying neuro-motor conditions of people with speech disorders, often compounded with co-occurring physical disabilities, lead to the difficulty in collecting large…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…