Related papers: BoSS: Beyond-Semantic Speech
Deep neural networks have largely demonstrated their ability to perform automated speech recognition (ASR) by extracting meaningful features from input audio frames. Such features, however, may consist not only of information about the…
We present a new task, speech dialogue translation mediating speakers of different languages. We construct the SpeechBSD dataset for the task and conduct baseline experiments. Furthermore, we consider context to be an important aspect that…
Emotion recognition in conversation (ERC), the task of discerning human emotions for each utterance within a conversation, has garnered significant attention in human-computer interaction systems. Previous ERC studies focus on…
Formal thought disorder (FTD), a hallmark of schizophrenia spectrum disorders, manifests as incoherent speech and poses challenges for clinical assessment. Traditional clinical rating scales, though validated, are resource-intensive and…
Modern communications are usually designed to pursue a higher bit-level precision and fewer bits while transmitting a message. This article rethinks these two major features and introduces the concept and advantage of semantics that…
The emergent few-shot reasoning capabilities of Large Language Models (LLMs) have excited the natural language and machine learning community over recent years. Despite of numerous successful applications, the underlying mechanism of such…
Aligning acoustic and linguistic representations is a central challenge to bridge the pre-trained models in knowledge transfer for automatic speech recognition (ASR). This alignment is inherently structured and asymmetric: while multiple…
Progress in speech processing has been facilitated by shared datasets and benchmarks. Historically these have focused on automatic speech recognition (ASR), speaker identification, or other lower-level tasks. Interest has been growing in…
Large language models have been extended to the speech domain, leading to the development of speech large language models (SLLMs). While existing SLLMs demonstrate strong performance in speech instruction-following for core languages (e.g.,…
Language models (LMs) have shown superior performances in various speech generation tasks recently, demonstrating their powerful ability for semantic context modeling. Given the intrinsic similarity between speech generation and speech…
Recent progress in auditory intelligence has yielded high-performing systems for sound event detection (SED), acoustic scene classification (ASC), automated audio captioning (AAC), and audio question answering (AQA). Yet these tasks remain…
State-of-the-art speech synthesis models try to get as close as possible to the human voice. Hence, modelling emotions is an essential part of Text-To-Speech (TTS) research. In our work, we selected FastSpeech2 as the starting point and…
Multi-turn dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection and answering questions. The major challenges involve noisy history contexts and especial prerequisites of…
Recent advances in machine learning, particularly deep learning, have enabled autonomous systems to perceive and comprehend objects and their environments in a perceptual subsymbolic manner. These systems can now perform object detection,…
Speech emotion recognition (SER) has made significant strides with the advent of powerful self-supervised learning (SSL) models. However, the generalization of these models to diverse languages and emotional expressions remains a challenge.…
Emotion recognition in speech presents a complex multimodal challenge, requiring comprehension of both linguistic content and vocal expressivity, particularly prosodic features such as fundamental frequency, intensity, and temporal…
Automatic speech recognition (ASR) is a core component of human--computer interaction and an increasingly important front-end for LLM-based assistants and agents. However, most current ASR systems still follow a single-pass paradigm, which…
Despite the ubiquity of large language models (LLMs) in AI research, the question of embodiment in LLMs remains underexplored, distinguishing them from embodied systems in robotics where sensory perception directly informs physical action.…
Deep learning enabled semantic communications have shown great potential to significantly improve transmission efficiency and alleviate spectrum scarcity, by effectively exchanging the semantics behind the data. Recently, the emergence of…
Cross-lingual representation learning transfers knowledge from resource-rich data to resource-scarce ones to improve the semantic understanding abilities of different languages. However, previous works rely on shallow unsupervised data…