Related papers: Adaptive Data Augmentation with NaturalSpeech3 for…

Deep neural network based speech enhancement approaches aim to learn a noisy-to-clean transformation using a supervised learning paradigm. However, such a trained-well transformation is vulnerable to unseen noises that are not included in…

While automatic speech recognition (ASR) systems have achieved remarkable performance with large-scale datasets, their efficacy remains inadequate in low-resource settings, encompassing dialects, accents, minority languages, and long-tail…

Automatic speaker verification (ASV) technology is recently finding its way to end-user applications for secure access to personal data, smart services or physical facilities. Similar to other biometric technologies, speaker verification is…

Accurate recognition of dysarthric and elderly speech remain challenging tasks to date. Speaker-level heterogeneity attributed to accent or gender, when aggregated with age and speech impairment, create large diversity among these speakers.…

Own voice pickup for hearables in noisy environments benefits from using both an outer and an in-ear microphone outside and inside the occluded ear. Due to environmental noise recorded at both microphones, and amplification of the own voice…

This paper describes noisy speech recognition for an augmented reality headset that helps verbal communication within real multiparty conversational environments. A major approach that has actively been studied in simulated environments is…

Automatic speech recognition (ASR) research has achieved impressive performance in recent years and has significant potential for enabling access for people with dysarthria (PwD) in augmentative and alternative communication (AAC) and home…

We explore cross-lingual multi-speaker speech synthesis and cross-lingual voice conversion applied to data augmentation for automatic speech recognition (ASR) systems in low/medium-resource scenarios. Through extensive experiments, we show…

The availability of data in expressive styles across languages is limited, and recording sessions are costly and time consuming. To overcome these issues, we demonstrate how to build low-resource, neural text-to-speech (TTS) voices with…

Many deep learning synthetic speech generation tools are readily available. The use of synthetic speech has caused financial fraud, impersonation of people, and misinformation to spread. For this reason forensic methods that can detect…

Speech enhancement has recently achieved great success with various deep learning methods. However, most conventional speech enhancement systems are trained with supervised methods that impose two significant challenges. First, a majority…

Augmenting the training data of automatic speech recognition (ASR) systems with synthetic data generated by text-to-speech (TTS) or voice conversion (VC) has gained popularity in recent years. Several works have demonstrated improvements in…

Rich sources of variability in natural speech present significant challenges to current data intensive speech recognition technologies. To model both speaker and environment level diversity, this paper proposes a novel Bayesian factorised…

To train transcriptor models that produce robust results, a large and diverse labeled dataset is required. Finding such data with the necessary characteristics is a challenging task, especially for languages less popular than English.…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

In this paper, we propose a method of speaker adaption with intuitive prosodic features for statistical parametric speech synthesis. The intuitive prosodic features employed in this method include pitch, pitch range, speech rate and energy…

This paper presents a statistical method of single-channel speech enhancement that uses a variational autoencoder (VAE) as a prior distribution on clean speech. A standard approach to speech enhancement is to train a deep neural network…

Spoken language understanding (SLU) systems often exhibit suboptimal performance in processing atypical speech, typically caused by neurological conditions and motor impairments. Recent advancements in Text-to-Speech (TTS) synthesis-based…

While recent text to speech (TTS) models perform very well in synthesizing reading-style (e.g., audiobook) speech, it is still challenging to synthesize spontaneous-style speech (e.g., podcast or conversation), mainly because of two…

Many neural text-to-speech architectures can synthesize nearly natural speech from text inputs. These architectures must be trained with tens of hours of annotated and high-quality speech data. Compiling such large databases for every new…