Related papers: U-vectors: Generating clusterable speaker embeddin…

The goal of this work is to train robust speaker recognition models without speaker labels. Recent works on unsupervised speaker representations are based on contrastive learning in which they encourage within-utterance embeddings to be…

The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…

Speaker embedding has been a fundamental feature for speaker-related tasks such as verification, clustering, and diarization. Traditionally, speaker embeddings are represented as fixed vectors in high-dimensional space. This could lead to…

We introduce "Unspeech" embeddings, which are based on unsupervised learning of context feature representations for spoken language. The embeddings were trained on up to 9500 hours of crawled English speech data without transcriptions or…

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…

Speaker embeddings are promising identity-related features that can enhance the identity assignment performance of a tracking system by leveraging its spatial predictions, i.e, by performing identity reassignment. Common speaker embedding…

Recently, researchers have utilized neural network-based speaker embedding techniques in speaker-recognition tasks to identify speakers accurately. However, speaker-discriminative embeddings do not always represent speech features such as…

The objective of this work is to train noise-robust speaker embeddings adapted for speaker diarisation. Speaker embeddings play a crucial role in the performance of diarisation systems, but they often capture spurious information such as…

One-shot voice conversion has received significant attention since only one utterance from source speaker and target speaker respectively is required. Moreover, source speaker and target speaker do not need to be seen during training.…

The current trend in automatic speech recognition is to leverage large amounts of labeled data to train supervised neural network models. Unfortunately, obtaining data for a wide range of domains to train robust models can be costly.…

Text mismatch between pre-collected data, either training data or enrollment data, and the actual test data can significantly hurt text-dependent speaker verification (SV) system performance. Although this problem can be solved by carefully…

This paper proposes a guided speaker embedding extraction system, which extracts speaker embeddings of the target speaker using speech activities of target and interference speakers as clues. Several methods for long-form overlapped…

Unsupervised word segmentation in audio utterances is challenging as, in speech, there is typically no gap between words. In a preliminary experiment, we show that recent deep self-supervised features are very effective for word…

An embedding-based speaker adaptive training (SAT) approach is proposed and investigated in this paper for deep neural network acoustic modeling. In this approach, speaker embedding vectors, which are a constant given a particular speaker,…

Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have…

Speaker clustering is an essential step in conventional speaker diarization systems and is typically addressed as an audio-only speech processing task. The language used by the participants in a conversation, however, carries additional…

Self-supervised learning (SSL) is a long-standing goal for speech processing, since it utilizes large-scale unlabeled data and avoids extensive human labeling. Recent years witness great successes in applying self-supervised learning in…

Despite rapid progress in the recent past, current speech recognition systems still require labeled training data which limits this technology to a small fraction of the languages spoken around the globe. This paper describes wav2vec-U,…

Domain mismatch between training and testing can lead to significant degradation in performance in many machine learning scenarios. Unfortunately, this is not a rare situation for automatic speech recognition deployments in real-world…

In this paper, we propose an effective training strategy to ex-tract robust speaker representations from a speech signal. Oneof the key challenges in speaker recognition tasks is to learnlatent representations or embeddings containing…