Related papers: Revisiting Group Differences in High-Dimensional C…
Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant…
In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…
Text-to-Speech (TTS) models have advanced significantly, aiming to accurately replicate human speech's diversity, including unique speaker identities and linguistic nuances. Despite these advancements, achieving an optimal balance between…
Large language models (LLMs) have demonstrated the ability to generate text that realistically reflects a range of different subjective human perspectives. This paper studies how LLMs are seemingly able to reflect more liberal versus more…
Recent works on end-to-end trainable neural network based approaches have demonstrated state-of-the-art results on dialogue state tracking. The best performing approaches estimate a probability distribution over all possible slot values.…
Some glottal analysis approaches based upon linear prediction or complex cepstrum approaches have been proved to be effective to estimate glottal source from real speech utterances. We propose a new approach employing both an all-pole…
We investigate whether one can determine from the transcripts of U.S. Congressional floor debates whether the speeches represent support of or opposition to proposed legislation. To address this problem, we exploit the fact that these…
In this paper, we conduct a comparative study on speaker-attributed automatic speech recognition (SA-ASR) in the multi-party meeting scenario, a topic with increasing attention in meeting rich transcription. Specifically, three approaches…
We introduce and analyze a novel approach to the problem of speaker identification in multi-party recorded meetings. Given a speech segment and a set of available candidate profiles, we propose a novel data-driven way to model the distance…
Quantitative methods to measure the participation to parliamentary debate and discourse of elected Members of Parliament (MPs) and the parties they belong to are lacking. This is an exploratory study in which we propose the development of a…
Recently, it has become easier to obtain speech data from various media such as the internet or YouTube, but directly utilizing them to train a neural text-to-speech (TTS) model is difficult. The proportion of clean speech is insufficient…
This paper introduces distribution-based prediction, a novel approach to using Large Language Models (LLMs) as predictive tools by interpreting output token probabilities as distributions representing the models' learned representation of…
This paper proposes a framework for modeling sound change that combines deep learning and iterative learning. Acquisition and transmission of speech is modeled by training generations of Generative Adversarial Networks (GANs) on unannotated…
In this article we present Enhanced Rhetorical Structure Theory (eRST), a new theoretical framework for computational discourse analysis, based on an expansion of Rhetorical Structure Theory (RST). The framework encompasses discourse…
This paper introduces "Semantic Scaling," a novel method for ideal point estimation from text. I leverage large language models to classify documents based on their expressed stances and extract survey-like data. I then use item response…
Sentence level pronunciation assessment is important for Computer Assisted Language Learning (CALL). Traditional speech pronunciation assessment, based on the Goodness of Pronunciation (GOP) algorithm, has some weakness in assessing a…
We explore the application of end-to-end stateless temporal modeling to small-footprint keyword spotting as opposed to recurrent networks that model long-term temporal dependencies using internal states. We propose a model inspired by the…
This article presents a probabilistic generative model for text based on semantic topics and syntactic classes called Part-of-Speech LDA (POSLDA). POSLDA simultaneously uncovers short-range syntactic patterns (syntax) and long-range…
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…
This paper introduces an online approach for identifying time-varying subspaces defined by linear dynamical systems. The approach of representing linear systems by non-parametric subspace models has received significant interest in the…