论文解读
被编解码器洗掉的水印：CRAW 如何把鲁棒性藏进听不见的地方
音频水印 | 7.7/10
语音编码
论文解读
不排队，各自说话再相加：PACodec 把量化从接力改成合唱
语音编码 | 7.1/10
论文解读
单塔为何还能赢双塔：BiMTokenizer 用双向状态与固定格点重做 1.1 kbps 的语义-声学平衡
语音编码 | 8.3/10
论文解读
当语音 Token 不再像自然语言：13 个编解码器在噪声下的语言统计学分化
语音编码 | 6.3/10
论文解读
口音的长尾，为什么让无监督语音表示最先露怯？
语音编码 | 5.5/10
论文解读
别让检测器猜伪迹：先把原声的压缩记忆藏回去
语音伪造检测 | 6.5/10
论文解读
想找回被替换的原话，先接受水印不能再像哈希那样精确
音频水印 | 6.4/10
论文解读
Speaker-Normalized Semantic Speech Tokens via Iterative S2U-T2U Refinement
语音编码 | 6.0/10
论文解读
Using the Mimi codec for metalinguistic representations
语音编码 | 4.7/10
论文解读
BAMU: Bitstream-Aware Marginal-Utility Allocation for Frozen Pretrained Neural Speech Codecs
语音编码 | 7.1/10
论文解读
ReLMCodec: Designing Predictable Speech Tokens from Pre-Quantization Phoneme Structure
语音编码 | 7.7/10
论文解读
LILAC: An Idempotent Neural Speech Codec
语音编码 | 8.1/10
论文解读
Assessing speech quality metrics for evaluation of neural audio codecs under clean speech conditions
语音质量评估 | 6.0/10
论文解读
Stable Autoregressive Speech Generation with Low-Frame-Rate High-Dimensional Continuous Tokens
语音合成 | 5.8/10
论文解读
Content is What Remains: Invariant Speech Tokenization from Parallel Utterances
语音编码 | 9.2/10
论文解读
CS-ETS: Chaos-Inspired Samba-Based EMG-To-Speech Synthesis with Nonlinear Chaotic Losses
语音合成 | 5.3/10
论文解读
ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
语音合成 | 7.5/10
论文解读
Text-Independent Speaker Verification Using Discrete Audio Tokens
说话人验证 | 5.2/10
论文解读
Speaker-Disentangled Chunk-Wise Regression for Syllabic Tokenization
语音编码 | 7.9/10
论文解读
Streaming Neural Speech Codecs through Time-Invariant Representations
语音编码 | 6.0/10