Related papers: Additive Margin SincNet for Speaker Recognition

For various speech-related tasks, confidence scores from a speech recogniser are a useful measure to assess the quality of transcriptions. In traditional hidden Markov model-based automatic speech recognition (ASR) systems, confidence…

End-to-end audio-conditioned latent diffusion models (LDMs) have been widely adopted for audio-driven portrait animation, demonstrating their effectiveness in generating lifelike and high-resolution talking videos. However, direct…

Despite the remarkable progress achieved on automatic speech recognition, recognizing far-field speeches mixed with various noise sources is still a challenging task. In this paper, we introduce novel student-teacher transfer learning,…

With the development of convolutional neural network, significant progress has been made in computer vision tasks. However, the commonly used loss function softmax loss and highly efficient network architecture for common visual tasks are…

Speaker Change Detection (SCD) is to identify boundaries among speakers in a conversation. Motivated by the success of fine-tuning wav2vec 2.0 models for the SCD task, a further investigation of self-supervised learning (SSL) features for…

We propose the application of a semi-supervised learning method to improve the performance of acoustic modelling for automatic speech recognition based on deep neural net- works. As opposed to unsupervised initialisation followed by…

With the rapid development of speech conversion and speech synthesis algorithms, automatic speaker verification (ASV) systems are vulnerable to spoofing attacks. In recent years, researchers had proposed a number of anti-spoofing methods…

Large Language Models are increasingly used as zero-shot classifiers in complex reasoning tasks. However, standard constrained decoding suffers from a phenomenon we define as Renormalization Bias. When a model is restricted to a small set…

Nowadays, deep learning is the standard approach for a wide range of problems, including biometrics, such as face recognition and speech recognition, etc. Biometric problems often use deep learning models to extract features from images,…

Multichannel speech enhancement (SE) aims to restore clean speech from noisy measurements by leveraging spatiotemporal signal features. In ad-hoc array conditions, microphone invariance (MI) requires systems to handle different microphone…

Softmax-based losses have achieved state-of-the-art performances on various tasks such as face recognition and re-identification. However, these methods highly relied on clean datasets with global labels, which limits their usage in many…

Spoofing detection systems are typically trained using diverse recordings from multiple speakers, often assuming that the resulting embeddings are independent of speaker identity. However, this assumption remains unverified. In this paper,…

Far-field speech processing is an important and challenging problem. In this paper, we propose \textit{deep ad-hoc beamforming}, a deep-learning-based multichannel speech enhancement framework based on ad-hoc microphone arrays, to address…

The Automatic Speaker Verification (ASV) system is vulnerable to fraudulent activities using audio deepfakes, also known as logical-access voice spoofing attacks. These deepfakes pose a concerning threat to voice biometrics due to recent…

As for the humanoid robots, the internal noise, which is generated by motors, fans and mechanical components when the robot is moving or shaking its body, severely degrades the performance of the speech recognition accuracy. In this paper,…

To better model the contextual information and increase the generalization ability of Speech Activity Detection (SAD) system, this paper leverages a multi-lingual Automatic Speech Recognition (ASR) system to perform SAD. Sequence…

Many endeavors have sought to develop countermeasure techniques as enhancements on Automatic Speaker Verification (ASV) systems, in order to make them more robust against spoof attacks. As evidenced by the latest ASVspoof 2019…

In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers…

Distributed microphone array (DMA) is a promising next-generation platform for speech interaction, where speech enhancement (SE) is still required to improve the speech quality in noisy cases. Existing SE methods usually first gather raw…

Accents, as variations from standard pronunciation, pose significant challenges for speech recognition systems. Although joint automatic speech recognition (ASR) and accent recognition (AR) training has been proven effective in handling…