相关论文: ClearerVoice-Studio: Bridging Advanced Speech Proc…

Audio-visual automatic speech recognition is a promising approach to robust ASR under noisy conditions. However, up until recently it had been traditionally studied in isolation assuming the video of a single speaking face matches the…

Speech pre-processing techniques such as denoising, de-reverberation, and separation, are commonly employed as front-ends for various downstream speech processing tasks. However, these methods can sometimes be inadequate, resulting in…

The development of robust, multilingual speaker recognition systems is hindered by a lack of large-scale, publicly available and multilingual datasets, particularly for the read-speech style crucial for applications like anti-spoofing. To…

The advancements of AI-synthesized human voices have introduced a growing threat of impersonation and disinformation. It is therefore of practical importance to developdetection methods for synthetic human voices. This work proposes a new…

With the growing requirement for natural human-computer interaction, speech-based systems receive increasing attention as speech is one of the most common forms of daily communication. However, the existing speech models still experience…

The goal of this work is to develop a meeting transcription system that can recognize speech even when utterances of different speakers are overlapped. While speech overlaps have been regarded as a major obstacle in accurately transcribing…

Singing voice conversion aims to transform a source singing voice into that of a target singer while preserving the original lyrics, melody, and various vocal techniques. In this paper, we propose a high-fidelity singing voice conversion…

Large speech generation models are evolving from single-speaker, short sentence synthesis to multi-speaker, long conversation geneartion. Current long-form speech generation models are predominately constrained to dyadic, turn-based…

We present Translatotron 2, a neural direct speech-to-speech translation model that can be trained end-to-end. Translatotron 2 consists of a speech encoder, a linguistic decoder, an acoustic synthesizer, and a single attention module that…

Systematic evaluation of speech separation and enhancement models under moving sound source conditions requires extensive and diverse data. However, real-world datasets often lack sufficient data for training and evaluation, and synthetic…

The creation of artificial polyglot voices remains a challenging task, despite considerable progress in recent years. This paper investigates self-supervised learning for voice conversion to create native-sounding polyglot voices. We…

The emergence of voice-assistant devices ushers in delightful user experiences not just on the smart home front, but also in diverse educational environments from classrooms to personalized-learning/tutoring. However, the use of voice as an…

Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this work, we introduce a family of models that enable end-to-end…

Over 70 million people worldwide experience stuttering, yet most automatic speech systems misinterpret disfluent utterances or fail to transcribe them accurately. Existing methods for stutter correction rely on handcrafted feature…

Separation of multiple singing voices into each voice is a rarely studied area in music source separation research. The absence of a benchmark dataset has hindered its progress. In this paper, we present an evaluation dataset and provide…

This paper reviews pioneering works in microphone array processing and multichannel speech enhancement, highlighting historical achievements, technological evolution, commercialization aspects, and key challenges. It provides valuable…

Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by…

Target speech extraction remains difficult for compact devices because monaural neural models lack spatial evidence and classical beamformers lose resolving power when the microphone aperture is only a few centimetres. We present IsoNet, a…

High-quality, large-scale audio captioning is crucial for advancing audio understanding, yet current automated methods often generate captions that lack fine-grained detail and contextual accuracy, primarily due to their reliance on limited…

This paper presents exploration of speech enable operating systems, software, and applications. It begins with a description of how such systems work, and the level of accuracy that can be expected. It explains the applications of speech…