Related papers: WenetSpeech: A 10000+ Hours Multi-domain Mandarin …
This paper presents a new large-scale Japanese speech corpus for training automatic speech recognition (ASR) systems. This corpus contains over 2,000 hours of speech with transcripts built on Japanese TV recordings and their subtitles. We…
Audio generation systems now create very realistic soundscapes that can enhance media production, but also pose potential risks. Several studies have examined deepfakes in speech or singing voice. However, environmental sounds have…
We introduce the largest transcribed Arabic speech corpus, QASR, collected from the broadcast domain. This multi-dialect speech dataset contains 2,000 hours of speech sampled at 16kHz crawled from Aljazeera news channel. The dataset is…
Modeling unit and model architecture are two key factors of Recurrent Neural Network Transducer (RNN-T) in end-to-end speech recognition. To improve the performance of RNN-T for Mandarin speech recognition task, a novel transformer…
Bengali is spoken by over 230 million people yet remains severely under-served in automatic speech recognition (ASR) and speaker diarization research. In this paper, we present our system for the DL Sprint 4.0 Bengali Long-Form Speech…
We present Ara-BEST-RQ, a family of self-supervised learning (SSL) models specifically designed for multi-dialectal Arabic speech processing. Leveraging 5,640 hours of crawled Creative Commons speech and combining it with publicly available…
We introduce a new dataset of conversational speech representing English from India, Nigeria, and the United States. The Multi-Dialect Dataset of Dialogues (MD3) strikes a new balance between open-ended conversational speech and…
While acoustic expressiveness has long been studied in expressive text-to-speech (ETTS), the inherent expressiveness in text lacks sufficient attention, especially for ETTS of artistic works. In this paper, we introduce StoryTTS, a highly…
Speech cloning technology is becoming more sophisticated thanks to the advances in machine learning. Researchers have successfully implemented natural-sounding English speech synthesis and good English speech cloning by some effective…
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…
Toxic speech on online platforms is a growing concern, impacting user experience and online safety. While text-based toxicity detection is well-studied, audio-based approaches remain underexplored, especially for low-resource languages like…
Cued Speech (CS) is a communication system developed for deaf people, which exploits hand cues to complement speechreading at the phonetic level. Currently, it is estimated that CS has been adapted to over 60 languages; however, no official…
Vietnamese, a low-resource language, is typically categorized into three primary dialect groups that belong to Northern, Central, and Southern Vietnam. However, each province within these regions exhibits its own distinct pronunciation…
We introduce an open source high-quality Mandarin TTS dataset MSceneSpeech (Multiple Scene Speech Dataset), which is intended to provide resources for expressive speech synthesis. MSceneSpeech comprises numerous audio recordings and texts…
Despite progress in audio classification, a generalization gap remains between speech and other sound domains, such as environmental sounds and music. Models trained for speech tasks often fail to perform well on environmental or musical…
Compared to news and chat summarization, the development of meeting summarization is hugely decelerated by the limited data. To this end, we introduce a versatile Chinese meeting summarization dataset, dubbed VCSum, consisting of 239…
This paper introduces the Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building…
Building Automatic Speech Recognition (ASR) systems from scratch is significantly challenging, mostly due to the time-consuming and financially-expensive process of annotating a large amount of audio data with transcripts. Although several…
Considering the bimodal nature of human speech perception, lips, and teeth movement has a pivotal role in automatic speech recognition. Benefiting from the correlated and noise-invariant visual information, audio-visual recognition systems…
In this paper, we present AISHELL-3, a large-scale and high-fidelity multi-speaker Mandarin speech corpus which could be used to train multi-speaker Text-to-Speech (TTS) systems. The corpus contains roughly 85 hours of emotion-neutral…