Image de couverture de livre

AHAMask: Reliable Task Specification for Large Audio Language Models without Instructions

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Guo, Yiwei, Li, Bohan, Wang, Hankun, Li, Zhihan, Wang, Shuai, Chen, Xie, Yu, Kai
Format:	Preprint
Publié:	2025
Sujets:	Audio and Speech Processing Artificial Intelligence Sound
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

ISA-Bench: Benchmarking Instruction Sensitivity for Large Audio Language Models
par: Li, Bohan, et autres
Publié: (2025)

Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency
par: Wang, Haoran, et autres
Publié: (2025)

CodecSlime: Temporal Redundancy Compression of Neural Speech Codec via Dynamic Frame Rate
par: Wang, Hankun, et autres
Publié: (2025)

Why Do Speech Language Models Fail to Generate Semantically Coherent Outputs? A Modality Evolving Perspective
par: Wang, Hankun, et autres
Publié: (2024)

Robust and Efficient Autoregressive Speech Synthesis with Dynamic Chunk-wise Prediction Policy
par: Li, Bohan, et autres
Publié: (2025)

Attention-Constrained Inference for Robust Decoder-Only Text-to-Speech
par: Wang, Hankun, et autres
Publié: (2024)

LSCodec: Low-Bitrate and Speaker-Decoupled Discrete Speech Codec
par: Guo, Yiwei, et autres
Publié: (2024)

vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders
par: Guo, Yiwei, et autres
Publié: (2024)

HoliTok:A Coutinuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
par: Li, Bohan, et autres
Publié: (2026)

Fast and High-Quality Auto-Regressive Speech Synthesis via Speculative Decoding
par: Li, Bohan, et autres
Publié: (2024)

VALL-T: Decoder-Only Generative Transducer for Robust and Decoding-Controllable Text-to-Speech
par: Du, Chenpeng, et autres
Publié: (2024)

On the Effectiveness of Acoustic BPE in Decoder-Only TTS
par: Li, Bohan, et autres
Publié: (2024)

Can Audio Large Language Models Verify Speaker Identity?
par: Ren, Yiming, et autres
Publié: (2025)

UniAudio 1.5: Large Language Model-driven Audio Codec is A Few-shot Audio Task Learner
par: Yang, Dongchao, et autres
Publié: (2024)

Recent Advances in Discrete Speech Tokens: A Review
par: Guo, Yiwei, et autres
Publié: (2025)

Pengi: An Audio Language Model for Audio Tasks
par: Deshmukh, Soham, et autres
Publié: (2023)

Audio-Mind: An Auditable Agentic Framework for Audio Understanding
par: Wang, Yucheng, et autres
Publié: (2026)

DiveSound: LLM-Assisted Automatic Taxonomy Construction for Diverse Audio Generation
par: Li, Baihan, et autres
Publié: (2024)

LEMAS: Large A 150K-Hour Large-scale Extensible Multilingual Audio Suite with Generative Speech Models
par: Zhao, Zhiyuan, et autres
Publié: (2026)

The Interspeech 2026 Audio Encoder Capability Challenge for Large Audio Language Models
par: Dinkel, Heinrich, et autres
Publié: (2026)

A Transcription Prompt-based Efficient Audio Large Language Model for Robust Speech Recognition
par: Li, Yangze, et autres
Publié: (2024)

Can Large Language Models Understand Spatial Audio?
par: Tang, Changli, et autres
Publié: (2024)

Unlocking Temporal Flexibility: Neural Speech Codec with Variable Frame Rate
par: Zhang, Hanglei, et autres
Publié: (2025)

VQTTS: High-Fidelity Text-to-Speech Synthesis with Self-Supervised VQ Acoustic Feature
par: Du, Chenpeng, et autres
Publié: (2022)

Unlocking Large Audio-Language Models for Interactive Language Learning
par: Liu, Hongfu, et autres
Publié: (2026)

HumDial-EIBench: A Human-Recorded Multi-Turn Emotional Intelligence Benchmark for Audio Language Models
par: Wang, Shuiyuan, et autres
Publié: (2026)

Summary on The Multilingual Conversational Speech Language Model Challenge: Datasets, Tasks, Baselines, and Methods
par: Mu, Bingshen, et autres
Publié: (2025)

UniCATS: A Unified Context-Aware Text-to-Speech Framework with Contextual VQ-Diffusion and Vocoding
par: Du, Chenpeng, et autres
Publié: (2023)

Contrastive Learning With Audio Discrimination For Customizable Keyword Spotting In Continuous Speech
par: Xi, Yu, et autres
Publié: (2024)

DSCLAP: Domain-Specific Contrastive Language-Audio Pre-Training
par: Liu, Shengqiang, et autres
Publié: (2024)

AeroGPT: Leveraging Large-Scale Audio Model for Aero-Engine Bearing Fault Diagnosis
par: Liu, Jiale, et autres
Publié: (2025)

Acoustic BPE for Speech Generation with Discrete Tokens
par: Shen, Feiyu, et autres
Publié: (2023)

MINT: Boosting Audio-Language Model via Multi-Target Pre-Training and Instruction Tuning
par: Zhao, Hang, et autres
Publié: (2024)

HearFit+: Personalized Fitness Monitoring via Audio Signals on Smart Speakers
par: Xie, Yadong, et autres
Publié: (2025)

A Survey on Speech Large Language Models for Understanding
par: Peng, Jing, et autres
Publié: (2024)

LongCat-Audio-Codec: An Audio Tokenizer and Detokenizer Solution Designed for Speech Large Language Models
par: Zhao, Xiaohan, et autres
Publié: (2025)

Jointly Recognizing Speech and Singing Voices Based on Multi-Task Audio Source Separation
par: Bai, Ye, et autres
Publié: (2024)

SEF-VC: Speaker Embedding Free Zero-Shot Voice Conversion with Cross Attention
par: Li, Junjie, et autres
Publié: (2023)

SongEditor: Adapting Zero-Shot Song Generation Language Model as a Multi-Task Editor
par: Yang, Chenyu, et autres
Publié: (2024)

Multi-Speaker Multi-Lingual VQTTS System for LIMMITS 2023 Challenge
par: Du, Chenpeng, et autres
Publié: (2023)