paper-with-me

홈 › Papers

Qwen2-Audio Technical Report

2024-07-15 · Yunfei Chu, Jin Xu, Qian Yang, Haojie Wei, Xipin Wei, Zhifang Guo, Yichong Leng, YuanJun Lv, Jinzheng He, Junyang Lin, Chang Zhou, Jingren Zhou

We introduce the latest progress of Qwen-Audio, a large-scale audio-language model called Qwen2-Audio, which is capable of accepting various audio signal inputs and performing audio analysis or direct textual responses with regard to speech instructions. In contrast to complex hierarchical tags, we have simplified the pre-training process by utilizing natural language prompts for different data and tasks, and have further expanded the data volume. We have boosted the instruction-following capability of Qwen2-Audio and implemented two distinct audio interaction modes for voice chat and audio analysis. In the voice chat mode, users can freely engage in voice interactions with Qwen2-Audio without text input. In the audio analysis mode, users could provide audio and text instructions for analysis during the interaction. Note that we do not use any system prompts to switch between voice chat and audio analysis modes. Qwen2-Audio is capable of intelligently comprehending the content within audio and following voice commands to respond appropriately. For instance, in an audio segment that simultaneously contains sounds, multi-speaker conversations, and a voice command, Qwen2-Audio can directly understand the command and provide an interpretation and response to the audio. Additionally, DPO has optimized the model's performance in terms of factuality and adherence to desired behavior. According to the evaluation results from AIR-Bench, Qwen2-Audio outperformed previous SOTAs, such as Gemini-1.5-pro, in tests focused on audio-centric instruction-following capabilities. Qwen2-Audio is open-sourced with the aim of fostering the advancement of the multi-modal language community.

📄 PDF Abstract BibTeX arXiv:2407.10759

Code (2)

qwenlm/qwen2-audio 공식 구현 pytorch
MindCode-4/code-4/tree/main/qwen2 mindspore

Tasks

Instruction FollowingLanguage Modelling

Methods 이 논문이 사용한 방법론

DPO 설명 없음

Similar Papers 제목 키워드 기반

Qwen2.5-Omni Technical Report

2025-03-26 · Jin Xu, Zhifang Guo, Jinzheng He, Hangrui Hu 외

In this report, we present Qwen2.5-Omni, an end-to-end multimodal model designed to perceive diverse modalities, including text, images, audio, and video, while simultaneously generating text and natural speech responses…

Automatic Speech Recognition (ASR)GSM8KInstruction FollowingLarge Language Model+4

Qwen3-Omni Technical Report

2025-09-22 · Jin Xu, Zhifang Guo, Hangrui Hu, Yunfei Chu 외 arxiv

We present Qwen3-Omni, a single multimodal model that, for the first time, maintains state-of-the-art performance across text, image, audio, and video without any degradation relative to single-modal counterparts. Qwen3-…

Multimodal ReasoningAudio captioning

Qwen-Audio-3.0-ASR Technical Report

2026-09-07 · Chuanmeng Bian, Daren Chen, Peixin Chen, Zhigao Chen 외 arxiv

In recent years, automatic speech recognition (ASR) has witnessed transformative advancements driven by three complementary paradigms: data scaling, model scaling, and deep integration with large language models (LLMs). …

Speech Recognition

Qwen-Music Technical Report

2026-07-13 · Jin Xu, Kangdi Wang, Ruibin Yuan, Shun Lei 외 hf

In this report, we introduce Qwen-Music, a powerful music generation model capable of producing highly musical and high-fidelity songs with complete vocal singing. Qwen-Music supports two core tasks: Text to Music Genera…

Music Generation

Qwen3-ASR Technical Report

2026-01-29 · Xian Shi, Xiong Wang, Zhifang Guo, Yongqi Wang 외 arxiv

In this report, we introduce Qwen3-ASR family, which includes two powerful all-in-one speech recognition models and a novel non-autoregressive speech forced alignment model. Qwen3-ASR-1.7B and Qwen3-ASR-0.6B are ASR mode…

Language IdentificationSpeech Recognition