相关论文: VocalNet-M2: Advancing Low-Latency Spoken Language…

Large Language Models (LLMs) are widely used in real-time voice chat applications, typically in combination with text-to-speech (TTS) systems to generate audio responses. However, their large size often leads to noticeable latency between…

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

This paper develops an edge-device collaborative Generative Semantic Communications (Gen SemCom) framework leveraging pre-trained Multi-modal/Vision Language Models (M/VLMs) for ultra-low-rate semantic communication via textual prompts. The…

Speech language models refer to language models with speech processing and understanding capabilities. One key desirable capability for speech language models is the ability to capture the intricate interdependency between content and…

Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so we generally need multiple tokens to express a complete…

Large language models (LLMs) have achieved notable progress. Despite their success, next-token prediction (NTP), the dominant method for LLM training and inference, is constrained in both contextual coverage and inference efficiency due to…

Audio-Visual Speech Recognition (AVSR) achieves robust speech recognition in noisy environments by combining auditory and visual information. However, recent Large Language Model (LLM) based AVSR systems incur high computational costs due…

Reasoning is essential for effective communication and decision-making. While recent advances in LLMs and MLLMs have shown that incorporating explicit reasoning significantly improves understanding and generalization, reasoning in LSMs…

Streaming voice conversion has become increasingly popular for its potential in real-time applications. The recently proposed DualVC 2 has achieved robust and high-quality streaming voice conversion with a latency of about 180ms.…

As large language models (LLMs) become increasingly powerful, the sequential nature of autoregressive generation creates a fundamental throughput bottleneck that limits the practical deployment. While Multi-Token Prediction (MTP) has…

Multimodal Large Language Models (MLLMs) have achieved significant success in Speech-to-Text Translation (S2TT) tasks. While most existing research has focused on English-centric translation directions, the exploration of many-to-many…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Multi-LLM systems harness the complementary strengths of diverse Large Language Models, achieving performance and efficiency gains that are not attainable by a single model. In existing designs, LLMs communicate through text, forcing…

Cascaded speech-to-speech translation systems often suffer from the error accumulation problem and high latency, which is a result of cascaded modules whose inference delays accumulate. In this paper, we propose a transducer-based speech…

Current text-to-speech (TTS) models face a persistent limitation: autoregressive (AR) models suffer from low generation efficiency, while modern non-autoregressive (NAR) models experience high latency due to their unordered temporal nature.…

Real-time Spoken Language Models (SLMs) struggle to leverage Chain-of-Thought (CoT) reasoning due to the prohibitive latency of generating the entire thought process sequentially. Enabling SLMs to think while speaking, similar to humans, is…

Unified architectures in multimodal large language models (MLLM) have shown promise in handling diverse tasks within a single framework. In the text-to-speech (TTS) task, current MLLM-based approaches rely on discrete token representations,…

Speech separation (SS) has advanced significantly with neural network-based methods, showing improved performance on signal-level metrics. However, these methods often struggle to maintain speech intelligibility in the separated signals,…

While the community keeps promoting end-to-end models over conventional hybrid models, which usually are long short-term memory (LSTM) models trained with a cross entropy criterion followed by a sequence discriminative training criterion,…

The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of…