TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

Hajo Nils Krabbenhöft; Erhardt Barth

doi:10.48550/ARXIV.2206.12693

TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

Hajo Nils Krabbenhöft, Erhardt Barth

Abstract

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.

Originalsprache	Englisch
Seitenumfang	10
Fachbuch	arXiv.org
Herausgeber (Verlag)	arXiv
DOIs	https://doi.org/10.48550/ARXIV.2206.12693
Publikationsstatus	Veröffentlicht - 25.06.2022

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

SDG 3 – Gesundheit und Wohlergehen
SDG 4 – Qualitativ hochwertige Bildung
SDG 9 – Industrie, Innovation und Infrastruktur
SDG 11 – Nachhaltige Städte und Gemeinschaften
SDG 12 – Verantwortungsvoller Konsum und Produktion
SDG 14 – Lebensraum Wasser
SDG 15 – Lebensraum Land

Strategische Forschungsbereiche und Zentren

Zentren: Zentrum für Künstliche Intelligenz Lübeck (ZKIL)
Querschnittsbereich: Intelligente Systeme

Dokumente

10.48550/ARXIV.2206.12693

https://arxiv.org/abs/2206.12693

Zitieren

@misc{d296d3dcc577472a9a40aeb2dae42432,

title = "TEVR: Improving Speech Recognition by Token Entropy Variance Reduction",

abstract = "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.",

author = "Krabbenh{\"o}ft, \{Hajo Nils\} and Erhardt Barth",

year = "2022",

month = jun,

day = "25",

doi = "10.48550/ARXIV.2206.12693",

language = "English",

journal = "arXiv.org",

publisher = "arXiv",

}

TY - GEN

T1 - TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

AU - Krabbenhöft, Hajo Nils

AU - Barth, Erhardt

PY - 2022/6/25

Y1 - 2022/6/25

N2 - 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.

AB - 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.

U2 - 10.48550/ARXIV.2206.12693

DO - 10.48550/ARXIV.2206.12693

M3 - Article

JO - arXiv.org

JF - arXiv.org

PB - arXiv

ER -

TEVR: Improving Speech Recognition by Token Entropy Variance Reduction

Abstract

UN SDGs

Strategische Forschungsbereiche und Zentren

Dokumente

Fingerprint

Zitieren