Related papers: Topic Model Robustness to Automatic Speech Recogni…

The recent advancement of large language models has spurred a growing trend of integrating pre-trained language model (PLM) embeddings into topic models, fundamentally reshaping how topics capture semantic structure. Classical models such…

Audio-text relevance learning refers to learning the shared semantic properties of audio samples and textual descriptions. The standard approach uses binary relevances derived from pairs of audio samples and their human-provided captions,…

Distinguishing scripted from spontaneous speech is an essential tool for better understanding how speech styles influence speech processing research. It can also improve recommendation systems and discovery experiences for media users…

Topic models jointly learn topics and document-level topic distribution. Extrinsic evaluation of topic models tends to focus exclusively on topic-level evaluation, e.g. by assessing the coherence of topics. We demonstrate that there can be…

In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose…

In the internet era there has been an explosion in the amount of digital text information available, leading to difficulties of scale for traditional inference algorithms for topic models. Recent advances in stochastic variational inference…

Podcasts have become a central arena for shaping public opinion, making them a vital source for understanding contemporary discourse. Their typically unscripted, multi-themed, and conversational style offers a rich but complex form of data.…

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…

Podcasts have recently shown a rapid rise in popularity. Summarization of podcast transcripts is of practical benefit to both content providers and consumers. It helps consumers to quickly decide whether they will listen to the podcasts and…

While recent automatic speech recognition systems achieve remarkable performance when large amounts of adequate, high quality annotated speech data is used for training, the same systems often only achieve an unsatisfactory result for tasks…

The optimization of a wavelet-based algorithm to improve speech intelligibility along with the full data set and results are reported. The discrete-time speech signal is split into frequency sub-bands via a multi-level discrete wavelet…

Human language is a combination of elemental languages/domains/styles that change across and sometimes within discourses. Language models, which play a crucial role in speech recognizers and machine translation systems, are particularly…

With the continuous development of deep learning-based speech conversion and speech synthesis technologies, the cybersecurity problem posed by fake audio has become increasingly serious. Previously proposed models for defending against fake…

Recently, there has been growth in providers of speech transcription services enabling others to leverage technology they would not normally be able to use. As a result, speech-enabled solutions have become commonplace. Their success…

Inferring topics from the overwhelming amount of short texts becomes a critical but challenging task for many content analysis tasks, such as content charactering, user interest profiling, and emerging topic detecting. Existing methods such…

Podcast summary, an important factor affecting end-users' listening decisions, has often been considered a critical feature in podcast recommendation systems, as well as many downstream applications. Existing abstractive summarization…

Podcast episodes often contain material extraneous to the main content, such as advertisements, interleaved within the audio and the written descriptions. We present classifiers that leverage both textual and listening patterns in order to…

Topic modelling is a text mining technique for identifying salient themes from a number of documents. The output is commonly a set of topics consisting of isolated tokens that often co-occur in such documents. Manual effort is often…

Topic segmentation is important in understanding scientific documents since it can not only provide better readability but also facilitate downstream tasks such as information retrieval and question answering by creating appropriate…

Deep Neural Networks (DNNs) have been shown to be susceptible to memorization or overfitting in the presence of noisily-labelled data. For the problem of robust learning under such noisy data, several algorithms have been proposed. A…