相关论文: Lost in Phonation: Voice Quality Variation as an E…

Speech Emotion Recognition (SER) systems often assume congruence between vocal emotion and lexical semantics. However, in real-world interactions, acoustic-semantic conflict is common yet overlooked, where the emotion conveyed by tone…

Speech foundation models (SFMs) have achieved state-of-the-art results for various speech tasks in supervised (e.g. Whisper) or self-supervised systems (e.g. WavLM). However, the performance of SFMs for child ASR has not been systematically…

Identity, accent, style, and emotions are essential components of human speech. Voice conversion (VC) techniques process the speech signals of two input speakers and other modalities of auxiliary information such as prompts and emotion…

Speech language models (SLMs) have significantly extended the interactive capability of text-based Large Language Models (LLMs) by incorporating paralinguistic information. For more realistic interactive experience with customized styles,…

Objective speech quality assessment is central to telephony, VoIP, and streaming systems, where large volumes of degraded audio must be monitored and optimized at scale. Classical metrics such as PESQ and POLQA approximate human mean…

Speech Language Models (SLMs) aim to learn language from raw audio, without textual resources. Despite significant advances, our current models exhibit weak syntax and semantic abilities. However, if the scaling properties of neural…

Understanding emotion from speech requires sensitivity to both lexical and acoustic cues. However, it remains unclear whether large audio language models (LALMs) genuinely process acoustic information or rely primarily on lexical content.…

Intrinsic evaluation metrics for conditional language models, such as perplexity or bits-per-character, are widely used in both mono- and multilingual settings. These metrics are rather straightforward to use and compare in monolingual…

Although paralinguistic cues are often considered the primary drivers of speech emotion recognition (SER), we investigate the role of lexical content extracted from speech and show that it can achieve competitive and in some cases higher…

Foundation models (FMs), including large language models, have become increasingly popular due to their wide-ranging applicability and ability to understand human-like semantics. While previous research has explored the use of FMs in…

Recent advances in emotional voice conversion (EVC) have enabled the generation of expressive synthetic speech, raising new concerns in audio deepfake detection. Existing approaches treat speech as a homogeneous signal and largely overlook…

The increasing use of children's automatic speech recognition (ASR) systems has spurred research efforts to improve the accuracy of models designed for children's speech in recent years. The current approach utilizes either open-source…

Recent advancements in large audio language models (LALMs) have demonstrated impressive results and promising prospects in universal understanding and reasoning across speech, music, and general sound. However, these models still lack the…

Singing Voice Conversion (SVC) is a technique that enables any singer to perform any song. To achieve this, it is essential to obtain speaker-agnostic representations from the source audio, which poses a significant challenge. A common…

Speech foundation models (SFMs), such as Open Whisper-Style Speech Models (OWSM), are trained on massive datasets to achieve accurate automatic speech recognition. However, even SFMs struggle to accurately recognize rare and unseen words.…

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…

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…

As Large Language Models (LLMs) expand beyond text, integrating speech as a native modality has given rise to SpeechLLMs, which directly process spoken language and enable speech-to-text translation (ST) and other downstream tasks,…

Recent years have seen a surge in the number of available frameworks for speech enhancement (SE) and recognition. Whether model-based or constructed via deep learning, these frameworks often rely in isolation on either time-domain signals…

Large language models exhibit systematic negation sensitivity, yet no operational framework exists to measure this vulnerability at deployment scale, especially in high-stakes decisions. We introduce Syntactic Framing Fragility (SFF), a…