Related papers: Unsupervised Speech Segmentation: A General Approa…

Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown…

In a hybrid speech model, both voiced and unvoiced components can coexist in a segment. Often, the voiced speech is regarded as the deterministic component, and the unvoiced speech and additive noise are the stochastic components.…

Recent neural supervised topic segmentation models achieve distinguished superior effectiveness over unsupervised methods, with the availability of large-scale training corpora sampled from Wikipedia. These models may, however, suffer from…

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…

With the advent of general-purpose speech representations from large-scale self-supervised models, applying a single model to multiple downstream tasks is becoming a de-facto approach. However, the pooling problem remains; the length of…

Although automatic emotion recognition (AER) has recently drawn significant research interest, most current AER studies use manually segmented utterances, which are usually unavailable for dialogue systems. This paper proposes integrating…

Since the first speech recognition systems were built more than 30 years ago, improvement in voice technology has enabled applications such as smart assistants and automated customer support. However, conversation intelligence of the future…

In this paper, we propose a sub-utterance unit selection framework to remove acoustic segments in audio recordings that carry little information for acoustic scene classification (ASC). Our approach is built upon a universal set of acoustic…

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…

Speech segmentation, which splits long speech into short segments, is essential for speech translation (ST). Popular VAD tools like WebRTC VAD have generally relied on pause-based segmentation. Unfortunately, pauses in speech do not…

Discovering speaker independent acoustic units purely from spoken input is known to be a hard problem. In this work we propose an unsupervised speaker normalization technique prior to unit discovery. It is based on separating speaker…

Language models provide a key framework for studying linguistic theories based on prediction, but phonological analysis using large language models (LLMs) is difficult; there are few phonological benchmarks beyond English and the standard…

Speech separation seeks to isolate individual speech signals from a multi-talk speech mixture. Despite much progress, a system well-trained on synthetic data often experiences performance degradation on out-of-domain data, such as…

Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by…

Speaker diarisation systems nowadays use embeddings generated from speech segments in a bottleneck layer, which are needed to be discriminative for unseen speakers. It is well-known that large-margin training can improve the generalisation…

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…

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain…

Speaker diarization is an important pre-processing step for many speech applications, and it aims to solve the "who spoke when" problem. Although the standard diarization systems can achieve satisfactory results in various scenarios, they…

Deep models trained on source domain lack generalization when evaluated on unseen target domains with different data distributions. The problem becomes even more pronounced when we have no access to target domain samples for adaptation. In…

Breaking down a document or a conversation into multiple contiguous segments based on its semantic structure is an important and challenging problem in NLP, which can assist many downstream tasks. However, current works on topic…