WeWorkBuddy

Named entitynamed-entitySteady

VoxMel

最近关注到一个挺有意思的开源 TTS 项目: VoxMel 。 GitHub: https://github.com/VoxDance-Lab/VoxMel Twitter: https://x.com/_akhaliq/status/2120749548851368358 现在不少自回归语音生成模型会依赖学习式声学 Tokenizer,先把音频离散化再进行建模。 VoxMel 的思路有点不一样,它尝试直接在连续 Mel 频谱上做自回归生成,不依赖学习式声学 Tokenizer,同时通过小波分解来组织不同尺度的声学信息。 感觉这个方向还挺值得探索的,毕竟如何在不引入离散声学 Token 的情况下实现高质量语音生成,一直是个挺有意思的问题。 项目已经开源了代码、模型和技术报告,也有音频 Demo 可以试听。 分享

This explanation quotes or summarizes the cited source record. Saving creates a bookmark on this device, with no automatic account sync.

First observed in our collection
Nov 16, 2026, 11:33 PM UTC
Earliest cited publication
Nov 15, 2026, 12:00 AM UTC
Last observed
Nov 17, 2026, 12:02 PM UTC

Evidence in the last complete seven days

Source mentions
2
Previous seven days 0
Distinct sources
2
Previous 0
Comparable growth
Not comparable
Ranking appearances
0

Collection observations and undated records are separate from dated publication counts. Observed in 7d:1 · Undated records:0

Collection coverage · Comparable windowsCurrent / previous observed days 7 / 7

Counts use complete UTC days. First observed means first seen by this collection, not when a term was coined.

Current window:2026-11-10 → 2026-11-17 (end excluded) · History 29 days

Observed source coverage by seven-day window
SourceCurrent daysPrevious daysLast success
arXiv67Nov 16, 2026, 1:19 PM UTC
arXiv77Nov 16, 2026, 1:19 PM UTC
Ask HN77Nov 17, 2026, 12:01 PM UTC
Ask HN77Nov 16, 2026, 11:33 PM UTC
Ask HN77Nov 16, 2026, 11:33 PM UTC
Ask HN77Nov 16, 2026, 11:33 PM UTC
Digg10Nov 17, 2026, 12:01 PM UTC
GitHub77Nov 17, 2026, 5:45 AM UTC
GitHub Issues77Nov 17, 2026, 5:45 AM UTC
GitHub Releases77Nov 17, 2026, 5:46 AM UTC
GitHub77Nov 17, 2026, 5:45 AM UTC
GitHub Issues77Nov 17, 2026, 5:45 AM UTC
GitHub Releases77Nov 17, 2026, 5:46 AM UTC
GitHub77Nov 17, 2026, 5:45 AM UTC
GitHub Issues77Nov 17, 2026, 5:45 AM UTC
GitHub Releases77Nov 17, 2026, 5:46 AM UTC
GitHub Discovery75Nov 17, 2026, 12:02 PM UTC
GitHub Trending77Nov 17, 2026, 12:01 PM UTC
Google77Nov 16, 2026, 1:19 PM UTC
Hackobar10Nov 17, 2026, 12:02 PM UTC
Hugging Face47Nov 16, 2026, 1:19 PM UTC
Hugging Face Spaces55Nov 17, 2026, 12:01 PM UTC
Hacker News77Nov 17, 2026, 12:01 PM UTC
Hacker News77Nov 16, 2026, 11:33 PM UTC
Hacker News77Nov 16, 2026, 11:34 PM UTC
Hacker News75Nov 17, 2026, 12:02 PM UTC
Show HN75Nov 17, 2026, 5:46 AM UTC
Microlaunch10Nov 16, 2026, 11:34 PM UTC
MIT News76Nov 16, 2026, 1:19 PM UTC
OpenAI77Nov 16, 2026, 1:19 PM UTC
Product Hunt77Nov 17, 2026, 12:02 PM UTC
量子位75Nov 16, 2026, 1:19 PM UTC
OpenRouter75Nov 17, 2026, 5:46 AM UTC
GitHub Trending37Nov 12, 2026, 4:00 AM UTC
Hugging Face Models55Nov 17, 2026, 12:02 PM UTC
HF Daily Papers54Nov 17, 2026, 12:02 PM UTC
OpenRouter75Nov 17, 2026, 5:46 AM UTC
Product Hunt37Nov 12, 2026, 4:00 AM UTC
SEC EDGAR77Nov 17, 2026, 5:45 AM UTC
Sequoia Capital77Nov 16, 2026, 1:19 PM UTC
Simon Willison75Nov 16, 2026, 1:19 PM UTC
TechCrunch77Nov 17, 2026, 12:01 PM UTC
Techmeme10Nov 17, 2026, 12:02 PM UTC
Trendshift10Nov 17, 2026, 12:02 PM UTC
Contracts Finder77Nov 17, 2026, 5:45 AM UTC
Uneed10Nov 17, 2026, 12:02 PM UTC
V2EX57Nov 17, 2026, 12:01 PM UTC
  • Counts describe monitored public sources, not the whole web or search demand.

Daily history · up to 90 days

Bars show dated source mentions. The latest UTC day may be incomplete. Zero mentions and missing collection coverage are different conditions.

2026-11-032026-11-17
View accessible daily data
Daily source mentions and collection observations
UTC dateMentionsSourcesObservationsRanking appearances
2026-11-030000
2026-11-040000
2026-11-050000
2026-11-060000
2026-11-070000
2026-11-080000
2026-11-090000
2026-11-100000
2026-11-110000
2026-11-120000
2026-11-130000
2026-11-140000
2026-11-151100
2026-11-161110
2026-11-170011
Source reference for [程序员] [开源分享] 发现一个挺有意思的 TTS 项目 VoxMel,直接在 Mel 频谱上做自回归生成. Screenshot not yet available.
Source record · preview pending · v2ex.comOpen the source for the full page.

Source evidence

Sources in the evidence shown:V2EX 1 · HF Daily Papers 1

  1. V2EX · Published Nov 16, 2026

    [程序员] [开源分享] 发现一个挺有意思的 TTS 项目 VoxMel,直接在 Mel 频谱上做自回归生成

    最近关注到一个挺有意思的开源 TTS 项目: VoxMel 。 GitHub: https://github.com/VoxDance-Lab/VoxMel Twitter: https://x.com/_akhaliq/status/2120749548851368358 现在不少自回归语音生成模型会依赖学习式声学 Tokenizer,先把音频离散化再进行建模。 VoxMel 的思路有点不一样,它尝试直接在连续 Mel 频谱上做自回归生成,不依赖学习式声学 Tokenizer,同时通过小波分解来组织不同尺度的声学信息。 感觉这个方向还挺值得探索的,毕竟如何在不引入离散声学 Token 的情况下实现高质量语音生成,一直是个挺有意思的问题。 项目已经开源了代码、模型和技术报告,也有音频 Demo 可以试听。 分享

    View source record →
  2. HF Daily Papers · Published Nov 15, 2026

    VoxMel TTS Technical Report

    Continuous autoregressive TTS relies on an acoustic target that enables stable next-latent modeling while preserving fine-grained acoustic details. While existing approaches employ learned compressed representations (e.g., continuous VAE latents) to render prediction tractable, they rely on complex neural encoders that often cap generation fidelity. Converse

Review priority 52 / 100

This score orders research candidates. It is not search volume, a forecast or verified commercial demand.

  • Evidence

    12.7 / 30

    Distinct dated articles or first observations; repeat crawling adds nothing.

  • Publisher diversity

    16 / 25

    Conservative owner grouping; syndicated copies count once.

  • Comparable change

    0 / 20

    Comparable complete weeks only; no percentage from a zero baseline.

  • Recent evidence

    15 / 15

    Latest publication or first observation, not repeated fetch time.

  • Name specificity

    7.8 / 10

    Explicit entities and technical concepts outrank ambiguous acronyms.

Limitations and interpretation

  • First observation is a collection milestone, not proof that a word or product is new to the world.
  • Counts describe monitored public sources, not the whole web or search demand.
  • First observed here is not the invention date of a name or idea.
  • Candidates come from public titles, summaries and entity URLs, not verified full-text analysis.
  • Owner grouping is conservative; undisclosed syndication may remain.
  • Repeat ranking appearances are observations, not new articles or independent endorsements.
  • The previous week is too small for a reliable percentage change.

← Back to New Term Radar