Related papers: 10 hours data is all you need

Recent advances in generating synthetic captions based on audio and related metadata allow using the information contained in natural language as input for other audio tasks. In this paper, we propose a novel method to guide a sound event…

The vast majority of modern speech enhancement systems rely on data-driven neural network models. Conventionally, larger datasets are presumed to yield superior model performance, an observation empirically validated across numerous tasks…

The existing audio datasets are predominantly tailored towards single languages, overlooking the complex linguistic behaviors of multilingual communities that engage in code-switching. This practice, where individuals frequently mix two or…

Recent advances in Automatic Speech Recognition (ASR) have been largely fueled by massive speech corpora. However, extending coverage to diverse languages with limited resources remains a formidable challenge. This paper introduces Speech…

Current state-of-the-art automatic speech recognition systems are trained to work in specific `domains', defined based on factors like application, sampling rate and codec. When such recognizers are used in conditions that do not match the…

The tasks of automatic lyrics transcription and lyrics alignment have witnessed significant performance improvements in the past few years. However, most of the previous works only focus on English in which large-scale datasets are…

Voice imitation aims to transform source speech to match a reference speaker's timbre and speaking style while preserving linguistic content. A straightforward approach is to train on triplets of (source, reference, target), where source…

Spoken Grammatical Error Correction (SGEC) and Feedback (SGECF) are crucial for second language learners, teachers and test takers. Traditional SGEC systems rely on a cascaded pipeline consisting of an ASR, a module for disfluency detection…

Speech pre-training has shown great success in learning useful and general latent representations from large-scale unlabeled data. Based on a well-designed self-supervised learning pattern, pre-trained models can be used to serve lots of…

For conversational large-vocabulary continuous speech recognition (LVCSR) tasks, up to about two thousand hours of audio is commonly used to train state of the art models. Collection of labeled conversational audio however, is prohibitively…

Thanks to the growing availability of spoofing databases and rapid advances in using them, systems for detecting voice spoofing attacks are becoming more and more capable, and error rates close to zero are being reached for the ASVspoof2015…

Singing voice conversion is converting the timbre in the source singing to the target speaker's voice while keeping singing content the same. However, singing data for target speaker is much more difficult to collect compared with normal…

Creating speech datasets, models, and evaluation frameworks for low-resource languages remains challenging given the lack of a broad base of pertinent experience to draw from. This paper reports on the field collection of 612 hours of…

Whilst recent neural text-to-speech (TTS) approaches produce high-quality speech, they typically require a large amount of recordings from the target speaker. In previous work, a 3-step method was proposed to generate high-quality TTS while…

End-to-end neural diarization (EEND) is nowadays one of the most prominent research topics in speaker diarization. EEND presents an attractive alternative to standard cascaded diarization systems since a single system is trained at once to…

The choice of modeling units is crucial for automatic speech recognition (ASR) tasks. In mandarin scenarios, the Chinese characters represent meaning but are not directly related to the pronunciation. Thus only considering the writing of…

Speaker verification is a typical zero-shot learning task, where inference of unseen classes is performed by comparing embeddings of test instances to known examples. The models performing inference must hence naturally generate embeddings…

Most existing neural-based text-to-speech methods rely on extensive datasets and face challenges under low-resource condition. In this paper, we introduce a novel semi-supervised text-to-speech synthesis model that learns from both paired…

AISHELL-1 is by far the largest open-source speech corpus available for Mandarin speech recognition research. It was released with a baseline system containing solid training and testing pipelines for Mandarin ASR. In AISHELL-2, 1000 hours…

Code-mixing (CM), where speakers blend languages within a single expression, is prevalent in multilingual societies but poses challenges for natural language processing due to its complexity and limited data. We propose using a large…