arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2606.29480eess.AScs.SD

DTM-Codec:基于高效边界选择的变帧率语音编码动态令牌掩码

DTM-Codec: Dynamic Token Masking for VFR Speech Coding with Efficient Boundary Selection

Graduate School of Cultural Technology, KAIST, South Korea(韩国科学技术院文化技术研究生院)

Hoyeol Sohn, Juhan Nam

AI总结:

提出DTM-Codec,通过动态令牌掩码和路径长度均衡(PLE)边界选择器,在严格匹配总比特率下优于固定帧率基线,提升重建质量和可懂度。

摘要:

变帧率(VFR)编码最近出现在神经语音编解码器中,为冗余区域分配更少的帧,为快速变化的语音分配更多的帧。VFR必须传输关于保留时间步长的边信息,但先前的增益要么没有得到严格处理,要么在将这些开销比特计入总比特率后通常很小。我们提出了动态令牌掩码(DTM)-Codec,一种神经语音编解码器,在严格匹配总比特率协议下,显示出相对于固定帧率基线的明显优势。DTM保留选定的编码器令牌,用学习的<MASK>嵌入填充掩码位置,并传输一个二值保留掩码用于位置感知解码。我们进一步引入了路径长度均衡(PLE),一种用于VFR编码的线性时间边界选择器,产生分布良好的自适应段,且开销可忽略。在不同的工作点上,DTM-Codec在重建质量和可懂度上普遍优于固定帧率基线。

英文摘要:

Variable frame rate (VFR) coding has recently emerged in neural speech codecs, allocating fewer frames to redundant regions and more frames to rapidly changing speech. VFR must transmit side information about retained time steps, but prior gains are either not rigorously addressed or often minor once these overhead bits are included in total bitrate. We present Dynamic Token Masking (DTM)-Codec, a neural speech codec that demonstrates clear gains over fixed-frame-rate baselines under a strict matched-total-bitrate protocol. DTM keeps selected encoder tokens, fills masked positions with a learned <MASK> embedding, and transmits a binary keep-mask for position-aware decoding. We further introduce Path Length Equalization (PLE), a linear-time boundary selector for VFR coding that yields well-spread adaptive segments with negligible overhead. Across operating points, DTM-Codec broadly improves reconstruction quality and intelligibility over fixed-frame-rate baselines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑