相关论文: What Are They Doing? Joint Audio-Speech Co-Reasoni…

In the field of spoken language processing, audio-visual speech processing is receiving increasing research attention. Key components of this research include tasks such as lip reading, audio-visual speech recognition, and visual-to-speech…

Multi-speaker automatic speech recognition (ASR) aims to transcribe conversational speech involving multiple speakers, requiring the model to capture not only what was said, but also who said it and sometimes when it was spoken. Recent…

Recently, there have been attempts to integrate various speech processing tasks into a unified model. However, few previous works directly demonstrated that joint optimization of diverse tasks in multitask speech models has positive…

Although Audio Large Language Models (ALLMs) have witnessed substantial advancements, their long audio understanding capabilities remain unexplored. A plethora of benchmarks have been proposed for general audio tasks, they predominantly…

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)…

We introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal…

Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. However, their scalability is limited by the quadratic complexity of attention and…

Speech inherently contains rich acoustic information that extends far beyond the textual language. In real-world spoken language understanding, effective interpretation often requires integrating semantic meaning (e.g., content),…

State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. However, it remains a challenge for these models to recognize overlapped speech,…

Recent work has shown that it is possible to train a single model to perform joint acoustic echo cancellation (AEC), speech enhancement, and voice separation, thereby serving as a unified frontend for robust automatic speech recognition…

Biologically inspired auditory models play an important role in developing effective audio representations that can be tightly integrated into speech and audio processing systems. Current computational models of the cochlea are typically…

We present a novel Speech Augmented Language Model (SALM) with {\em multitask} and {\em in-context} learning capabilities. SALM comprises a frozen text LLM, a audio encoder, a modality adapter module, and LoRA layers to accommodate speech…

Multimodal large language models (MLLMs) achieve strong performance by jointly processing inputs from multiple modalities, such as vision, audio, and language. However, building such models or extending them to new modalities often requires…

Recent advances in reasoning models have driven significant progress in text and multimodal domains, yet audio reasoning remains relatively limited. Only a few Large Audio Language Models (LALMs) incorporate explicit Chain-of-Thought (CoT)…

Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition…

Effective pronunciation feedback is critical in second language (L2) learning, for which computer-assisted pronunciation training (CAPT) systems often encompass two key tasks: automatic pronunciation assessment (APA) and mispronunciation…

This paper investigates adapting Audio Large Language Models (ALLMs) for speaker verification (SV). We reformulate SV as an audio question-answering task and conduct comprehensive zero-shot evaluations on public benchmarks, showing that…

Speaker-attributed automatic speech recognition (SA-ASR) is a task to recognize "who spoke what" from multi-talker recordings. An SA-ASR system usually consists of multiple modules such as speech separation, speaker diarization and ASR. On…

While Audio Large Models (ALMs) have achieved remarkable proficiency, their robustness remains brittle in real-world deployment. Existing evaluations largely rely on synthetic Gaussian noise or simplistic single-source interference, failing…

We introduce MMAR, a new benchmark designed to evaluate the deep reasoning capabilities of Audio-Language Models (ALMs) across massive multi-disciplinary tasks. MMAR comprises 1,000 meticulously curated audio-question-answer triplets,…