相关论文: Large-scale learning of generalised representation…

Deaf or hard-of-hearing (DHH) speakers typically have atypical speech caused by deafness. With the growing support of speech-based devices and software applications, more work needs to be done to make these devices inclusive to everyone. To…

In this paper we propose a new method of speaker diarization that employs a deep learning architecture to learn speaker embeddings. In contrast to the traditional approaches that build their speaker embeddings using manually hand-crafted…

Training machine learning algorithms for speech applications requires large, labeled training data sets. This is problematic for clinical applications where obtaining such data is prohibitively expensive because of privacy concerns or lack…

Transformer models have been used in automatic speech recognition (ASR) successfully and yields state-of-the-art results. However, its performance is still affected by speaker mismatch between training and test data. Further finetuning a…

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

Recently, there has been growing interest in multi-speaker speech recognition, where the utterances of multiple speakers are recognized from their mixture. Promising techniques have been proposed for this task, but earlier works have…

The wide deployment of speech-based biometric systems usually demands high-performance speaker recognition algorithms. However, most of the prior works for speaker recognition either process the speech in the frequency domain or time…

We introduce a sophisticated multi-speaker speech data simulator, specifically engineered to generate multi-speaker speech recordings. A notable feature of this simulator is its capacity to modulate the distribution of silence and overlap…

This paper presents a self-supervised learning framework, named MGF, for general-purpose speech representation learning. In the design of MGF, speech hierarchy is taken into consideration. Specifically, we propose to use generative learning…

Neural speaker diarization is widely used for overlap-aware speaker diarization, but it requires large multi-speaker datasets for training. To meet this data requirement, large datasets are often constructed by combining multiple corpora,…

While state-of-the-art neural network models continue to achieve lower perplexity scores on language modeling benchmarks, it remains unknown whether optimizing for broad-coverage predictive performance leads to human-like syntactic…

Speaker identification systems are deployed in diverse environments, often different from the lab conditions on which they are trained and tested. In this paper, first, we show the problem of generalization using fixed thresholds (computed…

Speaker extraction aims to extract target speech signal from a multi-talker environment with interference speakers and surrounding noise, given the target speaker's reference information. Most speaker extraction systems achieve satisfactory…

This is a report of our lessons learned building acoustic models from 1 Million hours of unlabeled speech, while labeled speech is restricted to 7,000 hours. We employ student/teacher training on unlabeled data, helping scale out target…

The task of estimating the maximum number of concurrent speakers from single channel mixtures is important for various audio-based applications, such as blind source separation, speaker diarisation, audio surveillance or auditory scene…

With excellent generalization ability, self-supervised speech models have shown impressive performance on various downstream speech tasks in the pre-training and fine-tuning paradigm. However, as the growing size of pre-trained models,…

Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single-speaker scenarios, it prevents accurate detection when the…

We present an end-to-end deep network model that performs meeting diarization from single-channel audio recordings. End-to-end diarization models have the advantage of handling speaker overlap and enabling straightforward handling of…

Learned feature representations and sub-phoneme posteriors from Deep Neural Networks (DNNs) have been used separately to produce significant performance gains for speaker and language recognition tasks. In this work we show how these gains…

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…