相关论文: Tongue pressure recordings during speech using com…

Accented text-to-speech (TTS) synthesis seeks to generate speech with an accent (L2) as a variant of the standard version (L1). Accented TTS synthesis is challenging as L2 is different from L1 in both in terms of phonetic rendering and…

Existing datasets for audio understanding primarily focus on single-turn interactions (i.e. audio captioning, audio question answering) for describing audio in natural language, thus limiting understanding audio via interactive dialogue. To…

We introduce a monaural neural speaker embeddings extractor that computes an embedding for each speaker present in a speech mixture. To allow for supervised training, a teacher-student approach is employed: the teacher computes the target…

Human speech is often accompanied by hand and arm gestures. Given audio speech input, we generate plausible gestures to go along with the sound. Specifically, we perform cross-modal translation from "in-the-wild'' monologue speech of a…

Humans involuntarily tend to infer parts of the conversation from lip movements when the speech is absent or corrupted by external noise. In this work, we explore the task of lip to speech synthesis, i.e., learning to generate natural…

The noise of a device under test (DUT) is measured simultaneously with two instruments, each of which contributes its own background. The average cross power spectral density converges to the DUT power spectral density. This method enables…

Collapsible tubes can be employed to study the sound generation mechanism in the human respiratory system. The goals of this work are (a) to determine the airflow characteristics connected to three different collapse states of a…

The goal of this contribution is to use a parametric speech synthesis system for reducing background noise and other interferences from recorded speech signals. In a first step, Hidden Markov Models of the synthesis system are trained. Two…

The speech signal is a consummate example of time-series data. The acoustics of the signal change over time, sometimes dramatically. Yet, the most common type of comparison we perform in phonetics is between instantaneous acoustic…

The analysis of speech measures in individuals with amyotrophic lateral sclerosis (ALS) can provide essential information for early diagnosis and tracking disease progression. However, current methods for extracting speech and pause…

The aim of this project was to develop and implement an English language Text-to-Speech synthesis system. This involved a study of mechanisms of human speech production, a review of techniques in speech synthesis, and analysis of tests used…

Sound production due to turbulence is widely shown to be an important phenomenon involved in a.o. fricatives, singing, whispering and speech pathologies. In spite of its relevance turbulent flow is not considered in classical physical…

The development of novel texture adaptations for the management of swallowing disorders could be accelerated if reliable in vitro tests were made available. This study addresses some of the limitations of swallowing in vitro models, by…

Recent advancements in audio-driven talking face generation have made great progress in lip synchronization. However, current methods often lack sufficient control over facial animation such as speaking style and emotional expression,…

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…

Prosody plays a vital role in verbal communication. Acoustic cues of prosody have been examined extensively. However, prosodic characteristics are not only perceived auditorily, but also visually based on head and facial movements. The…

Recent advancements in speech-driven 3D talking head generation have made significant progress in lip synchronization. However, existing models still struggle to capture the perceptual alignment between varying speech characteristics and…

Hand interactions are increasingly used as the primary input modality in immersive environments, but they are not always feasible due to situational impairments, motor limitations, and environmental constraints. Speech interfaces have been…

The human ear canal couples the external sound field to the eardrum and the solid parts of the middle ear. Therefore, knowledge of the acoustic impedance of the human ear is widely used in the industry to develop audio devices such as…

Many hearables contain an in-ear microphone, which may be used to capture the own voice of its user. However, due to the hearable occluding the ear canal, the in-ear microphone mostly records body-conducted speech, typically suffering from…