Related papers: Large Speech Model Enabled Semantic Communication
Semantic communication technology emerges as a pivotal bridge connecting AI with classical communication. The current semantic communication systems are generally modeled as an Auto-Encoder (AE). AE lacks a deep integration of AI principles…
Recently, Mixture of Experts (MoE) based Transformer has shown promising results in many domains. This is largely due to the following advantages of this architecture: firstly, MoE based Transformer can increase model capacity without…
Large language models (LLMs) have significantly advanced audio processing through audio codecs that convert audio into discrete tokens, enabling the application of language modelling techniques to audio data. However, traditional codecs…
Existing deep learning based speech enhancement mainly employ a data-driven approach, which leverage large amounts of data with a variety of noise types to achieve noise removal from noisy signal. However, the high dependence on the data…
The advent of 6G networks demands unprecedented levels of intelligence, adaptability, and efficiency to address challenges such as ultra-high-speed data transmission, ultra-low latency, and massive connectivity in dynamic environments.…
Recently, the ever-increasing demand for bandwidth in multi-modal communication systems requires a paradigm shift. Powered by deep learning, semantic communications are applied to multi-modal scenarios to boost communication efficiency and…
Spoken Language Models (SLMs) are increasingly central to modern speech-driven applications, but performance degrades under acoustic shift - real-world noise, reverberation, and microphone variation. Prior solutions rely on offline domain…
Spurred by a huge interest in the post-Shannon communication, it has recently been shown that leveraging semantics can significantly improve the communication effectiveness across many tasks. In this article, inspired by human…
Text-to-Speech (TTS) models can generate natural, human-like speech across multiple languages by transforming phonemes into waveforms. However, multilingual TTS remains challenging due to discrepancies in phoneme vocabularies and variations…
This paper explores the potential of constructing an AI spoken dialogue system that "thinks how to respond" and "thinks how to speak" simultaneously, which more closely aligns with the human speech production process compared to the current…
Autoregressive next-token prediction with the Transformer decoder has become a de facto standard in large language models (LLMs), achieving remarkable success in Natural Language Processing (NLP) at scale. Extending this paradigm to audio…
Modeling the speaker variability is a key challenge for automatic speech recognition (ASR) systems. In this paper, the learning hidden unit contributions (LHUC) based adaptation techniques with compact speaker dependent (SD) parameters are…
Recent works have shown promising results in connecting speech encoders to large language models (LLMs) for speech recognition. However, several limitations persist, including limited fine-tuning options, a lack of mechanisms to enforce…
With the availability of massive general-domain dialogue data, pre-trained dialogue generation appears to be super appealing to transfer knowledge from the general domain to downstream applications. In most existing work, such transferable…
Speech tokenizers are essential for connecting speech to large language models (LLMs) in multimodal systems. These tokenizers are expected to preserve both semantic and acoustic information for downstream understanding and generation.…
Semantic-oriented communication has been considered as a promising to boost the bandwidth efficiency by only transmitting the semantics of the data. In this paper, we propose a multi-level semantic aware communication system for wireless…
In NLP, text language models based on words or subwords are known to outperform their character-based counterparts. Yet, in the speech community, the standard input of spoken LMs are 20ms or 40ms-long discrete units (shorter than a…
Speech language models (Speech LMs) enable end-to-end speech-text modeling within a single model, offering a promising direction for spoken dialogue systems. The choice of speech-text jointly decoding paradigm plays a critical role in…
With the advent of Fifth Generation (5G) and Sixth Generation (6G) communication technologies, as well as the Internet of Things (IoT), semantic communication is gaining attention among researchers as current communication technologies are…
Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…