相关论文: Soundwave: Less is More for Speech-Text Alignment …

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…

We study speech language models that incorporate semantic initialization and planning losses to achieve robust and consistent generation. Our approach initializes speech tokens with self-supervised features, applies a light alignment loss,…

The recent surge in open-source Multimodal Large Language Models (MLLM) frameworks, such as LLaVA, provides a convenient kickoff for artificial intelligence developers and researchers. However, most of the MLLM frameworks take vision as the…

Simultaneous speech-to-text translation systems must balance translation quality with latency. Although quality evaluation is well established, latency measurement remains a challenge. Existing metrics produce inconsistent results,…

Training large-scale models presents challenges not only in terms of resource requirements but also in terms of their convergence. For this reason, the learning rate (LR) is often decreased when the size of a model is increased. Such a…

Speech-to-speech translation (S2ST) has been advanced with large language models (LLMs), which are fine-tuned on discrete speech units. In such approaches, modality adaptation from text to speech has been an issue. LLMs are trained on…

Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex…

Large Audio Language Models (LALM) combine the audio perception models and the Large Language Models (LLM) and show a remarkable ability to reason about the input audio, infer the meaning, and understand the intent. However, these systems…

Self-supervised learning (SSL) methods such as WavLM have shown promising speech separation (SS) results in small-scale simulation-based experiments. In this work, we extend the exploration of the SSL-based SS by massively scaling up both…

Audio chaptering, the task of segmenting long-form audio into coherent sections, is increasingly important for navigating podcasts, lectures, and videos. Despite its relevance, research remains limited and text-based, leaving key questions…

Real-time speech-to-speech (S2S) models excel at generating natural, low-latency conversational responses but often lack deep knowledge and semantic understanding. Conversely, cascaded systems combining automatic speech recognition, a…

In this study, we aim to explore Multitask Speech Language Model (SpeechLM) efficient inference via token reduction. Unlike other modalities such as vision or text, speech has unique temporal dependencies, making previous efficient…

High-quality audio is essential in a wide range of applications, including online communication, virtual assistants, and the multimedia industry. However, degradation caused by noise, compression, and transmission artifacts remains a major…

The high incidence and mortality rates associated with respiratory diseases underscores the importance of early screening. Machine learning models can automate clinical consultations and auscultation, offering vital support in this area.…

The rapid growth of voice assistants powered by large language models (LLM) has highlighted a need for speech instruction data to train these systems. Despite the abundance of speech recognition data, there is a notable scarcity of speech…

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…

Listening to audio content, such as podcasts and audiobooks, is one way for people to engage with knowledge. Listening affords people more mobility than reading by seeing, thereby broadening their learning opportunities. This study explores…

Textless spoken language models (SLMs) are generative models of speech that do not rely on text supervision. Most textless SLMs learn to predict the next semantic token, a discrete representation of linguistic content, and rely on a…

Most lip-to-speech (LTS) synthesis models are trained and evaluated under the assumption that the audio-video pairs in the dataset are perfectly synchronized. In this work, we show that the commonly used audio-visual datasets, such as GRID,…

Current end-to-end spoken language models (SLMs) have made notable progress, yet they still encounter considerable response latency. This delay primarily arises from the autoregressive generation of speech tokens and the reliance on complex…