语音翻译 on 语音/音频论文速递 https://nanless.github.io/audio-paper-digest-blog/tags/%E8%AF%AD%E9%9F%B3%E7%BF%BB%E8%AF%91/ Recent content in 语音翻译 on 语音/音频论文速递 Hugo zh-cn Wed, 29 Apr 2026 00:00:00 +0000 Advancing Speech Understanding in Speech-Aware Language Models with GRPO https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-understanding-in-speech-aware/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-advancing-speech-understanding-in-speech-aware/ 语音问答 | 7.0/10 ATOM: Adaptive Token-Level Optimal Transport Mixup for Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-atom-adaptive-token-level-optimal-transport-mixup/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-atom-adaptive-token-level-optimal-transport-mixup/ 语音翻译 | 8.0/10 Attention2Probability: Attention-Driven Terminology Probability Estimation for Robust Speech-to-text System https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention2probability-attention-driven/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-attention2probability-attention-driven/ 语音识别 | 7.0/10 Chunk-Wise Attention Transducers for Fast and Accurate Streaming Speech-to-Text https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-chunk-wise-attention-transducers-for-fast-and/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-chunk-wise-attention-transducers-for-fast-and/ 语音识别 | 7.5/10 Direct Simultaneous Translation Activation for Large Audio-Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-simultaneous-translation-activation-for/ 语音翻译 | 6.0/10 Direct Transfer of Prosody in Speech-to-speech Translation using Disentangled Speech Tokens https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-transfer-of-prosody-in-speech-to-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-direct-transfer-of-prosody-in-speech-to-speech/ 语音翻译 | 7.5/10 Equipping Large Language Model with Directional Speech Understanding Capabilities https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-equipping-large-language-model-with-directional/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-equipping-large-language-model-with-directional/ 语音识别 语音翻译 | 7.0/10 ICASSP 2026 - 语音翻译 论文列表 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-074/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/icassp2026-task-074/ 共 8 篇 ICASSP 2026 语音翻译 方向论文 Joint Autoregressive Modeling of Multi-Talker Overlapped Speech Recognition and Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-joint-autoregressive-modeling-of-multi-talker/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-joint-autoregressive-modeling-of-multi-talker/ 语音识别 语音翻译 | 7.0/10 LESS: Large Language Model Enhanced Semi-Supervised Learning for Speech Foundational Models Using in-the-wild Data https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-less-large-language-model-enhanced-semi/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-less-large-language-model-enhanced-semi/ 语音识别 语音翻译 | 7.5/10 LongSpeech: A Scalable Benchmark for Transcription, Translation and Understanding in Long Speech https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-longspeech-a-scalable-benchmark-for-transcription/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-longspeech-a-scalable-benchmark-for-transcription/ 基准测试 | 7.8/10 MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-Token Prediction https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mtp-s2ut-enhancing-speech-to-speech-translation/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-mtp-s2ut-enhancing-speech-to-speech-translation/ 语音翻译 | 8.5/10 nGPT as a Scalable Architecture for Speech Recognition and Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ngpt-as-a-scalable-architecture-for-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-ngpt-as-a-scalable-architecture-for-speech/ 语音识别 | 7.5/10 Phrased: Phrase Dictionary Biasing for Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-phrased-phrase-dictionary-biasing-for-speech/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-phrased-phrase-dictionary-biasing-for-speech/ 语音翻译 | 7.5/10 PROST-LLM: Progressively Enhancing the Speech-to-Speech Translation Capability in LLMs https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-prost-llm-progressively-enhancing-the-speech-to/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-prost-llm-progressively-enhancing-the-speech-to/ 语音翻译 | 7.5/10 Revisiting Direct Speech-to-Text Translation with Speech LLMS: Better Scaling than Cot Prompting? https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-revisiting-direct-speech-to-text-translation-with/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-revisiting-direct-speech-to-text-translation-with/ 语音翻译 | 7.5/10 SEP-ST: Incorporating Speech Entity Prompt Into Large Language Models for Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sep-st-incorporating-speech-entity-prompt-into/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-sep-st-incorporating-speech-entity-prompt-into/ 语音翻译 | 7.5/10 SLM-TTA: A Framework for Test-Time Adaptation of Generative Spoken Language Models https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-tta-a-framework-for-test-time-adaptation-of/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-slm-tta-a-framework-for-test-time-adaptation-of/ 语音识别 | 7.0/10 TTA: Transcribe, Translate and Alignment for Cross-Lingual Speech Representation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tta-transcribe-translate-and-alignment-for-cross/ Wed, 29 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-29-tta-transcribe-translate-and-alignment-for-cross/ 语音识别 | 7.5/10 Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-hierarchical-policy-optimization-for-simultaneous/ Fri, 24 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-24-hierarchical-policy-optimization-for-simultaneous/ 语音翻译 | 7.5/10 MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-move-translating-laughter-and-tears-via-mixture/ Thu, 23 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-23-move-translating-laughter-and-tears-via-mixture/ 这篇论文旨在解决语音到语音翻译（S2ST）系统普遍丢失源语音中非语言声音（如笑声、哭声）和情感信息的问题，这严重影响了跨语言交流的自然度和准确性。为此，作者提出了三项核心贡献：首先，设计了一个可扩展的自动化数据合成管道，用于生成大规模、高质量的英中富有表现力S2ST平行语料，克服了训练数据稀缺的瓶颈 Detecting Hallucinations in SpeechLLMs at Inference Time Using Attention Maps https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-detecting-hallucinations-in-speechllms-at/ Wed, 22 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-22-detecting-hallucinations-in-speechllms-at/ 本文旨在解决语音大模型（SpeechLLMs）在推理时产生的“幻觉”问题，即生成与输入音频不符的流畅文本。现有方法依赖昂贵的黄金标准输出，而文本LLM的方法无法捕捉音频特有信号。为此，作者提出了四个基于注意力图的轻量级指标（AudioRatio, AudioConsistency, AudioEnt MoVE: Translating Laughter and Tears via Mixture of Vocalization Experts in Speech-to-Speech Translation https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-move-translating-laughter-and-tears-via-mixture/ Tue, 21 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-21-move-translating-laughter-and-tears-via-mixture/ 这篇论文旨在解决语音到语音翻译（S2ST）系统普遍缺失非语言声音（如笑声、哭泣）和情感韵律的问题，这严重限制了跨语言交流的自然度和语用准确性。作者提出了三大贡献：1) 一个**可扩展的表达性数据合成管道**，能自动生成高质量、带情感标注的S2ST训练对，克服了数据稀缺瓶颈；2) **MoVE（混合声 NaijaS2ST: A Multi-Accent Benchmark for Speech-to-Speech Translation in Low-Resource Nigerian Languages https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-naijas2st-a-multi-accent-benchmark-for-speech-to/ Mon, 20 Apr 2026 00:00:00 +0000 https://nanless.github.io/audio-paper-digest-blog/posts/2026-04-20-naijas2st-a-multi-accent-benchmark-for-speech-to/ 这篇论文旨在解决非洲低资源语言在语音翻译（S2ST和S2TT）研究中面临的高质量、多口音平行语音数据严重匮乏的核心瓶颈。为此，作者构建了**NaijaS2ST**数据集，涵盖豪萨语、伊博语、约鲁巴语和尼日利亚皮钦语与英语的平行语音，每种语言约50小时，捕获了真实的说话者与口音多样性。基于此数据集，论