Related papers: PRODIS -- a speech database and a phoneme-based la…
Modelling the process that a listener actuates in deriving the words intended by a speaker requires setting a hypothesis on how lexical items are stored in memory. This work aims at developing a system that imitates humans when identifying…
Modern neural text-to-speech (TTS) synthesis can generate speech that is indistinguishable from natural speech. However, the prosody of generated utterances often represents the average prosodic style of the database instead of having wide…
Pre-trained Language Models (PLMs) are known to contain various kinds of knowledge. One method to infer relational knowledge is through the use of cloze-style prompts, where a model is tasked to predict missing subjects or objects.…
Language-audio joint representation learning frameworks typically depend on deterministic embeddings, assuming a one-to-one correspondence between audio and text. In real-world settings, however, the language-audio relationship is…
In this paper, we present a database of emotional speech intended to be open-sourced and used for synthesis and generation purpose. It contains data for male and female actors in English and a male actor in French. The database covers 5…
A new language model for speech recognition inspired by linguistic analysis is presented. The model develops hidden hierarchical structure incrementally and uses it to extract meaningful information from the word history - thus enabling the…
Recent research in zero-shot speech synthesis has made significant progress in speaker similarity. However, current efforts focus on timbre generalization rather than prosody modeling, which results in limited naturalness and…
Phrases are essential to understand the core concepts in conversations. However, due to their rare occurrence in training data, correct translation of phrases is challenging in speech translation tasks. In this paper, we propose a phrase…
We tackle the prediction of instructor intervention in student posts from discussion forums in Massive Open Online Courses (MOOCs). Our key finding is that using automatically obtained discourse relations improves the prediction of when…
Methods for learning sentence representations have been actively developed in recent years. However, the lack of pre-trained models and datasets annotated at the sentence level has been a problem for low-resource languages such as Polish…
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribution, whereas the…
Conversations contain a wide spectrum of multimodal information that gives us hints about the emotions and moods of the speaker. In this paper, we developed a system that supports humans to analyze conversations. Our main contribution is…
Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…
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…
Large-scale pre-trained language models have been shown to be helpful in improving the naturalness of text-to-speech (TTS) models by enabling them to produce more naturalistic prosodic patterns. However, these models are usually word-level…
Neural text-to-speech systems are often optimized on L1/L2 losses, which make strong assumptions about the distributions of the target data space. Aiming to improve those assumptions, Normalizing Flows and Diffusion Probabilistic Models…
Prosody plays a crucial role in speech perception, influencing both human understanding and automatic speech recognition (ASR) systems. Despite its importance, prosodic stress remains under-studied due to the challenge of efficiently…
The DIAlogue MOdel Learning Environment supports an engineering-oriented approach towards dialogue modelling for a spoken-language interface. Major steps towards dialogue models is to know about the basic units that are used to construct a…
Describes an audio dataset of spoken words designed to help train and evaluate keyword spotting systems. Discusses why this task is an interesting challenge, and why it requires a specialized dataset that is different from conventional…
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…