相关论文: A Principle Solution for Enroll-Test Mismatch in S…

End-to-end speaker diarization enables accurate overlap-aware diarization by jointly estimating multiple speakers' speech activities in parallel. This approach is data-hungry, requiring a large amount of labeled conversational data, which…

We consider the scene text recognition problem under the attention-based encoder-decoder framework, which is the state of the art. The existing methods usually employ a frame-wise maximal likelihood loss to optimize the models. When we…

Speech separation has been extensively explored to tackle the cocktail party problem. However, these studies are still far from having enough generalization capabilities for real scenarios. In this work, we raise a common strategy named…

We study a novel neural architecture and its training strategies of speaker encoder for speaker recognition without using any identity labels. The speaker encoder is trained to extract a fixed-size speaker embedding from a spoken utterance…

This paper presents a robust multi-channel speaker extraction algorithm designed to handle inaccuracies in reference information. While existing approaches often rely solely on either spatial or spectral cues to identify the target speaker,…

We study example-level private supervised speech classification under a practical release constraint: training may access privileged side information, but the released model must be audio-only. This setting is important because speech…

Speaker verification systems are vulnerable to spoofing attacks which presents a major problem in their real-life deployment. To date, most of the proposed synthetic speech detectors (SSDs) have weighted the importance of different segments…

Disentangled representation learning in speech processing has lagged behind other domains, largely due to the lack of datasets with annotated generative factors for robust evaluation. To address this, we propose SynSpeech, a novel…

In this paper, we propose Self-Contrastive Decorrelation (SCD), a self-supervised approach. Given an input sentence, it optimizes a joint self-contrastive and decorrelation objective. Learning a representation is facilitated by leveraging…

Surface crack segmentation poses a challenging computer vision task as background, shape, colour and size of cracks vary. In this work we propose optimized deep encoder-decoder methods consisting of a combination of techniques which yield…

The current monaural state of the art tools for speech separation relies on supervised learning. This means that they must deal with permutation problem, they are impacted by the mismatch on the number of speakers used in training and…

This work explores how self-supervised learning can be universally used to discover speaker-specific features towards enabling personalized speech enhancement models. We specifically address the few-shot learning scenario where access to…

Some audio declipping methods produce waveforms that do not fully respect the physical process of clipping, which is why we refer to them as inconsistent. This letter reports what effect on perception it has if the solution by inconsistent…

In this work, we propose an overlapped speech detection system trained as a three-class classifier. Unlike conventional systems that perform binary classification as to whether or not a frame contains overlapped speech, the proposed…

In this paper, we perform an in-depth study of how data augmentation techniques improve synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel variability, different audio compressions, different…

Probabilistic linear discriminant analysis (PLDA) or cosine similarity have been widely used in traditional speaker verification systems as back-end techniques to measure pairwise similarities. To make better use of multiple enrollment…

Spoken language change detection (LCD) refers to identifying the language transitions in a code-switched utterance. Similarly, identifying the speaker transitions in a multispeaker utterance is known as speaker change detection (SCD). Since…

Preference optimization is widely used to align large language models (LLMs) with human preferences. However, many margin-based methods also suppress the chosen response when they try to suppress the rejected one, and there is no general…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved…

Most speech separation methods, trying to separate all channel sources simultaneously, are still far from having enough general- ization capabilities for real scenarios where the number of input sounds is usually uncertain and even dynamic.…