Related papers: Investigation for Relative Voice Impression Estima…

Speech quality assessment has been a critical issue in speech processing for decades. Existing automatic evaluations usually require clean references or parallel ground truth data, which is infeasible when the amount of data soars.…

Large Language Model-based Voice Assistants (LLM-VAs) are increasingly deployed in assistive settings for older adults, yet little is known about how an agent's personality shapes user perceptions of its explanations. This paper presents a…

Estimating dimensional emotions, such as activation, valence and dominance, from acoustic speech signals has been widely explored over the past few years. While accurate estimation of activation and dominance from speech seem to be…

Our voices are as distinctive as our faces and fingerprints. There is a spectrum of non-disjoint traits that make our voices unique and identifiable, such as the fundamental frequency, the intensity, and most interestingly the quality of…

This work aims at investigating and analyzing speaker identification in each unbiased and biased emotional talking environments based on a classifier called Suprasegmental Hidden Markov Models (SPHMMs). The first talking environment is…

Several established parameters and metrics have been used to characterize the acoustics of a room. The most important are the Direct-To-Reverberant Ratio (DRR), the Reverberation Time (T60) and the reflection coefficient. The acoustic…

Speech large language models (LLMs) observe paralinguistic cues such as prosody, emotion, and non-verbal sounds--crucial for intent understanding. However, leveraging these cues faces challenges: limited training data, annotation…

Acoustic context effects, where surrounding changes in pitch, rate or timbre influence the perception of a sound, are well documented in speech perception, but how they interact with language background remains unclear. Using a…

Speech-comprehension difficulties are common among older people. Standard speech tests do not fully capture such difficulties because the tests poorly resemble the context-rich, story-like nature of ongoing conversation and are typically…

Audio Large Language Models (Audio LLMs) have demonstrated strong capabilities in integrating speech perception with language understanding. However, whether their internal representations align with human neural dynamics during…

Standard benchmarks of bias and fairness in large language models (LLMs) measure the association between the user attributes stated or implied by a prompt and the LLM's short text response, but human-AI interaction increasingly requires…

Compositional reasoning in Vision-Language Models (VLMs) remains challenging as these models often struggle to relate objects, attributes, and spatial relationships. Recent methods aim to address these limitations by relying on the…

To build speech processing methods that can handle speech as naturally as humans, researchers have explored multiple ways of building an invertible mapping from speech to an interpretable space. The articulatory space is a promising…

Large Audio-Language Models (LALMs) are enhanced with audio perception capabilities, enabling them to effectively process and understand multimodal inputs that combine audio and text. However, their performance in handling conflicting…

An end-to-end (E2E) ASR model implicitly learns a prior Internal Language Model (ILM) from the training transcripts. To fuse an external LM using Bayes posterior theory, the log likelihood produced by the ILM has to be accurately estimated…

Recent work in the domain of speech enhancement has explored the use of self-supervised speech representations to aid in the training of neural speech enhancement models. However, much of this work focuses on using the deepest or final…

Various parametric representations have been proposed to model the speech signal. While the performance of such vocoders is well-known in the context of speech processing, their extrapolation to singing voice synthesis might not be…

We present a self-supervised learning method to learn audio and video representations. Prior work uses the natural correspondence between audio and video to define a standard cross-modal instance discrimination task, where a model is…

With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent…

We propose a novel approach for blind room impulse response (RIR) estimation systems in the context of a downstream application scenario, far-field automatic speech recognition (ASR). We first draw the connection between improved RIR…