Phone Segmentation and Recognition through Phonological Activation Mapping

  • 类型：arxiv
  • 标识：2607.09020
  • 链接：https://arxiv.org/abs/2607.09020
  • 主分类：multimodal
  • 形态：method
  • 被引：0
  • 被引来源：Semantic Scholar + OpenAlex
  • S2被引：0
  • OpenAlex被引：0
  • 影响力被引：0
  • TLDR：It is argued that phonetic structure is already latent in the representations of self-supervised speech models (S3Ms), and one only needs to steer them to solve both segmentation and recognition tasks.
  • OpenAlex ID：W7168184922
  • OpenAlex DOI：10.48550/arxiv.2607.09020
  • DOI：10.48550/arxiv.2607.09020
  • DOI来源：OpenAlex
  • 开放获取：green
  • 开放获取链接：https://doi.org/10.48550/arxiv.2607.09020
  • OpenAlex更新：2026-07-19
  • 待LLM分类：否
  • 标题中文：基于音韵激活映射的音素切分与识别
  • TLDR中文：论文主张语音结构已隐含在自监督语音模型（S3M）的表征中，只需对其进行引导即可同时完成切分与识别任务。
  • 来源文件：
  • /inbox/tom/_candidates/2026-07-13-agent-rag-longcontext-candidates.json
  • [S2 enrich]
  • /inbox/tom/_candidates/2026-07-14-rag-retrieval-reranking-candidates.json
  • /inbox/tom/_candidates/2026-07-14-agent-rag-longcontext-candidates.json
  • [OpenAlex backfill]