相关论文: Self-supervised pre-training with acoustic configu…

Current audio pre-training seeks to learn unified representations for broad audio understanding tasks, but it remains fragmented and is fundamentally bottlenecked by its reliance on weak, noisy, and scale-limited labels. Drawing lessons…

In this work, we provide a broad comparative analysis of strategies for pre-training audio understanding models for several tasks in the music domain, including labelling of genre, era, origin, mood, instrumentation, key, pitch, vocal…

This paper addresses source tracing in synthetic speech-identifying generative systems behind manipulated audio via speaker recognition-inspired pipelines. While prior work focuses on spoofing detection, source tracing lacks robust…

This paper describes our proposed integration system for the spoofing-aware speaker verification challenge. It consists of a robust spoofing-aware verification system that use the speaker verification and antispoofing embeddings extracted…

Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to…

We explore pretraining strategies including choice of base corpus with the aim of choosing the best strategy for zero-shot multi-speaker end-to-end synthesis. We also examine choice of neural vocoder for waveform synthesis, as well as…

Audio recorded in real-world environments often contains a mixture of foreground speech and background environmental sounds. With rapid advances in text-to-speech, voice conversion, and other generation models, either component can now be…

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…

Research in speaker recognition has recently seen significant progress due to the application of neural network models and the availability of new large-scale datasets. There has been a plethora of work in search for more powerful…

When watching videos, the occurrence of a visual event is often accompanied by an audio event, e.g., the voice of lip motion, the music of playing instruments. There is an underlying correlation between audio and visual events, which can be…

Automatic Speaker Verification (ASV) suffers from performance degradation in noisy conditions. To address this issue, we propose a novel adversarial learning framework that incorporates noise-disentanglement to establish a noise-independent…

Fusing outputs from automatic speaker verification (ASV) and spoofing countermeasure (CM) is expected to make an integrated system robust to zero-effort imposters and synthesized spoofing attacks. Many score-level fusion methods have been…

Face spoofing causes severe security threats in face recognition systems. Previous anti-spoofing works focused on supervised techniques, typically with either binary or auxiliary supervision. Most of them suffer from limited robustness and…

Wav2vec2.0 is a popular self-supervised pre-training framework for learning speech representations in the context of automatic speech recognition (ASR). It was shown that wav2vec2.0 has a good robustness against the domain shift, while the…

Despite the significant improvements in speaker recognition enabled by deep neural networks, unsatisfactory performance persists under noisy environments. In this paper, we train the speaker embedding network to learn the "clean" embedding…

It is well known that speaker verification systems are subject to spoofing attacks. The Automatic Speaker Verification Spoofing and Countermeasures Challenge -- ASVSpoof2015 -- provides a standard spoofing database, containing attacks based…

We present a multimodal framework to learn general audio representations from videos. Existing contrastive audio representation learning methods mainly focus on using the audio modality alone during training. In this work, we show that…

Face anti-spoofing has drawn a lot of attention due to the high security requirements in biometric authentication systems. Bringing face biometric to commercial hardware became mostly dependent on developing reliable methods for detecting…

Self-supervised representation learning can mitigate the limitations in recognition tasks with few manually labeled data but abundant unlabeled data---a common scenario in sound event research. In this work, we explore unsupervised…

We propose an explainable probabilistic framework for characterizing spoofed speech by decomposing it into probabilistic attribute embeddings. Unlike raw high-dimensional countermeasure embeddings, which lack interpretability, the proposed…