按年被提到
20222022 · 2 次2026
视觉、语音与图像生成›语音与音频生成·arXiv:2206.12693 · cs.CL

TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

Hajo Nils Krabbenhöft, Erhardt Barth · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2022-08-10 · 最近 2026-06-12
2不同的人
4活跃月份
4讨论串
3被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This paper presents TEVR, a speech recognition model designed to minimize the variation in token entropy w.r.t. to the language model. This takes advantage of the fact that if the language model will reliably and accurately predict a token anyway, then the acoustic model doesn't need to be accurate in recognizing it. We train German ASR models with 900 million parameters and show that on CommonVoice German, TEVR scores a very competitive 3.64% word error rate, which outperforms the best reported results by a relative 16.89% reduction in word error rate. We hope that releasing our fully trained speech recognition pipeline to the community will lead to privacy-preserving offline virtual assistants in the future.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论nshm · 2022-08

“This model seems strongly overtrained on CV test set. Usually improvement from LM rescoring is just 10% relative. In the paper https://arxiv.org/pdf/2206.12693.pdf the improvement is from 10.1% WER to 3.64% WER (Table 6). Such a big improvement suggests that LM is biased. Also, the perplexity of provided ngram LM on CV test set is just 86 and most of 5-g…”

Show HN: State-of-the-art German speech recognition in 284 lines of C++原评论 ↗
评论fxtentacle · 2022-11

“In this paper https://arxiv.org/abs/2206.12693 I show that choosing the text snippets deliberately so that your choices minimize overall entropy will also minimize result entropy, meaning it'll increase the accuracy of your speech recognition system (for German speech).”

Vision Transformers (ViT) Explained原评论 ↗
评论fxtentacle · 2025-10

“That also works purely on text and it's the trick I used in my German speech recognition engine ( https://arxiv.org/abs/2206.12693 ). "I'm studying at Oxford Univ" has basically no loss in meaning even though "University" was truncated to less than half its characters.”

DeepSeek OCR原评论 ↗
评论fxtentacle · 2026-06

“This is an interesting approach with integer programming and then using an explicit solver. It’s probably very slow, but you only have to run this once and it produces the mathematically perfect result. In the past, I got good results with trying to reduce the variance in entropy in-between tokens, which you can implement very easily by starting with eac…”

Finding Optimal Tokenizers原评论 ↗