相关论文: Exploring the Use of an Unsupervised Autoregressiv…

Conventional audio-visual methods for speaker verification rely on large amounts of labeled data and separate modality-specific architectures, which is computationally expensive, limiting their scalability. To address these problems, we…

This paper introduces an efficient and accurate pipeline for text-dependent speaker verification (TDSV), designed to address the need for high-performance biometric systems. The proposed system incorporates a Fast-Conformer-based ASR module…

Learning speaker-specific features is vital in many applications like speaker recognition, diarization and speech recognition. This paper provides a novel approach, we term Neural Predictive Coding (NPC), to learn speaker-specific…

Disentangled representation learning aims to extract explanatory features or factors and retain salient information. Factorized hierarchical variational autoencoder (FHVAE) presents a way to disentangle a speech signal into sequential-level…

Audiovisual active speaker detection (ASD) is conventionally performed by modelling the temporal synchronisation of acoustic and visual speech cues. In egocentric recordings, however, the efficacy of synchronisation-based methods is…

In this paper, we address the problem of speaker verification in conditions unseen or unknown during development. A standard method for speaker verification consists of extracting speaker embeddings with a deep neural network and processing…

In this letter, we propose a vocal tract length (VTL) perturbation method for text-dependent speaker verification (TD-SV), in which a set of TD-SV systems are trained, one for each VTL factor, and score-level fusion is applied to make a…

We present a bidirectional unsupervised model pre-training (UPT) method and apply it to children's automatic speech recognition (ASR). An obstacle to improving child ASR is the scarcity of child speech databases. A common approach to…

The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other…

Autoregressive Predictive Coding (APC), as a self-supervised objective, has enjoyed success in learning representations from large amounts of unlabeled data, and the learned representations are rich for many downstream tasks. However, the…

This paper describes our submission to Task 1 of the Short-duration Speaker Verification (SdSV) challenge 2020. Task 1 is a text-dependent speaker verification task, where both the speaker and phrase are required to be verified. The…

Audiovisual active speaker detection (ASD) addresses the task of determining the speech activity of a candidate speaker given acoustic and visual data. Typically, systems model the temporal correspondence of audiovisual cues, such as the…

Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have…

In speech processing pipelines, improving the quality and intelligibility of real-world recordings is crucial. While supervised regression is the primary method for speech enhancement, audio tokenization is emerging as a promising…

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…

This paper proposes a novel technique to obtain better downstream ASR performance from a joint encoder-decoder self-supervised model when trained with speech pooled from two different channels (narrow and wide band). The joint…

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

Despite the growing interest in unsupervised learning, extracting meaningful knowledge from unlabelled audio remains an open challenge. To take a step in this direction, we recently proposed a problem-agnostic speech encoder (PASE), that…

In this paper, we initiate the concern of enhancing the spoofing robustness of the automatic speaker verification (ASV) system, without the primary presence of a separate countermeasure module. We start from the standard ASV framework of…

Self-supervision has shown great potential for audio-visual speech recognition by vastly reducing the amount of labeled data required to build good systems. However, existing methods are either not entirely end-to-end or do not train joint…