相关论文: Interpretable Temporal Class Activation Representa…

We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data. We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech…

Recently, there have been tremendous research outcomes in the fields of speech recognition and natural language processing. This is due to the well-developed multi-layers deep learning paradigms such as wav2vec2.0, Wav2vecU, WavBERT, and…

Current state-of-the-art automatic speaker verification (ASV) systems are vulnerable to presentation attacks, and several countermeasures (CMs), which distinguish bona fide trials from spoofing ones, have been explored to protect ASV.…

Despite several years of research in deepfake and spoofing detection for automatic speaker verification, little is known about the artefacts that classifiers use to distinguish between bona fide and spoofed utterances. An understanding of…

Recent findings show that pre-trained wav2vec 2.0 models are reliable feature extractors for various speaker characteristics classification tasks. We show that latent representations extracted at different layers of a pre-trained wav2vec…

Recently, self-supervised pre-training has shown significant improvements in many areas of machine learning, including speech and NLP. We propose using large self-supervised pre-trained models for both audio and text modality with…

In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of…

Multilingual speech recognition with supervised learning has achieved great results as reflected in recent research. With the development of pretraining methods on audio and text data, it is imperative to transfer the knowledge from…

In this work, we introduce a multi-task transformer for speech deepfake detection, capable of predicting formant trajectories and voicing patterns over time, ultimately classifying speech as real or fake, and highlighting whether its…

Child speech recognition is still an underdeveloped area of research due to the lack of data (especially on non-English languages) and the specific difficulties of this task. Having explored various architectures for child speech…

This study explores a multi-lingual audio self-supervised learning model for detecting mild cognitive impairment (MCI) using the TAUKADIAL cross-lingual dataset. While speech transcription-based detection with BERT models is effective,…

Active speaker detection and speech enhancement have become two increasingly attractive topics in audio-visual scenario understanding. According to their respective characteristics, the scheme of independently designed architecture has been…

It becomes urgent to design effective anti-spoofing algorithms for vulnerable automatic speaker verification systems due to the advancement of high-quality playback devices. Current studies mainly treat anti-spoofing as a binary…

Pseudo-label learning methods have been widely applied in weakly-supervised temporal action localization. Existing works directly utilize weakly-supervised base model to generate instance-level pseudo-labels for training the…

In this paper, we present a novel training method for speaker change detection models. Speaker change detection is often viewed as a binary sequence labelling problem. The main challenges with this approach are the vagueness of annotated…

Emotion recognition datasets are relatively small, making the use of the more sophisticated deep learning approaches challenging. In this work, we propose a transfer learning method for speech emotion recognition where features extracted…

ASR systems designed for native English (L1) usually underperform on non-native English (L2). To address this performance gap, \textbf{(i)} we extend our previous work to investigate fine-tuning of a pre-trained wav2vec 2.0 model…

Recent advances in neural text-to-speech research have been dominated by two-stage pipelines utilizing low-level intermediate speech representation such as mel-spectrograms. However, such predetermined features are fundamentally limited,…

In this paper, we present our submitted XMUspeech systems to the speech deepfake detection track of the ASVspoof 5 Challenge. Compared to previous challenges, the audio duration in ASVspoof 5 database has significantly increased. And we…

Audio deepfake detection systems trained on one dataset often fail when deployed on data from different sources due to distributional shifts in recording conditions, synthesis methods, and acoustic environments. We present a modular…