相关论文: SepALM: Audio Language Models Are Error Correctors…

Despite the success of deep learning in speech recognition, multi-dialect speech recognition remains a difficult problem. Although dialect-specific acoustic models are known to perform well in general, they are not easy to maintain when…

Automatic Speech Recognition (ASR) traditionally assumes known domains, but adding data from a new domain raises concerns about computational inefficiencies linked to retraining models on both existing and new domains. Fine-tuning solely on…

Continuous speech separation plays a vital role in complicated speech related tasks such as conversation transcription. The separation model extracts a single speaker signal from a mixed speech. In this paper, we use transformer and…

We recently developed SLM, a joint speech and language model, which fuses a pretrained foundational speech model and a large language model (LLM), while preserving the in-context learning capability intrinsic to the pretrained LLM. In this…

Recent advancements in Large Audio Language Models (LALMs) have demonstrated exceptional performance in speech recognition and translation. However, existing models often suffer from a disconnect between perception and expression, resulting…

We develop a large language model (LLM) based automatic speech recognition (ASR) system that can be contextualized by providing keywords as prior information in text prompts. We adopt decoder-only architecture and use our in-house LLM,…

One of the central skills that language learners need to practice is speaking the language. Currently, students in school do not get enough speaking opportunities and lack conversational practice. Recent advances in speech technology and…

While large language models have demonstrated impressive reasoning abilities, their extension to the audio modality, particularly within large audio-language models (LALMs), remains underexplored. Addressing this gap requires a systematic…

This paper presents the Interspeech 2026 Audio Encoder Capability Challenge, a benchmark specifically designed to evaluate and advance the performance of pre-trained audio encoders as front-end modules for Large Audio Language Models…

Speech separation in realistic acoustic environments remains challenging because overlapping speakers, background noise, and reverberation must be resolved simultaneously. Although recent time-frequency (TF) domain models have shown strong…

Recent speech language models rely on encoders that are optimized separately from autoregressive models. Since these encoders are unaware of the downstream objectives, the extracted representations may not be optimal for downstream tasks.…

In this paper, we introduce an unsupervised approach for Speech Segmentation, which builds on previously researched approaches, e.g., Speaker Diarization, while being applicable to an inclusive set of acoustic-semantic distinctions, paving…

Speech-to-Speech (S2S) Large Language Models (LLMs) are foundational to natural human-computer interaction, enabling end-to-end spoken dialogue systems. However, evaluating these models remains a fundamental challenge. We propose…

Despite the tremendous success of automatic speech recognition (ASR) with the introduction of deep learning, its performance is still unsatisfactory in many real-world multi-talker scenarios. Speaker separation excels in separating…

Multimodal large language models (MLLMs) have recently become a focal point of research due to their formidable multimodal understanding capabilities. For example, in the audio and speech domains, an LLM can be equipped with (automatic)…

Silent Speech Interfaces (SSIs) have gained attention for their ability to generate intelligible speech from non-acoustic signals. While significant progress has been made in advancing speech generation pipelines, limited work has addressed…

Recent advancements in large language models (LLMs) have revolutionized various domains, bringing significant progress and new opportunities. Despite progress in speech-related tasks, LLMs have not been sufficiently explored in multi-talker…

Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR architectures connect a speech encoder to a large language model via a projection module,…

Transcribing meetings containing overlapped speech with only a single distant microphone (SDM) has been one of the most challenging problems for automatic speech recognition (ASR). While various approaches have been proposed, all previous…

Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, current DLMs have been studied at a smaller scale compared to…