paper-with-me

홈 › Papers

Contextual Earnings-22: A Speech Recognition Benchmark with Custom Vocabulary in the Wild

2026-03-28 · Berkin Durmus, Chen Cen, Eduardo Pacheco, Arda Okan, Atila Orhon arxiv

The accuracy frontier of speech-to-text systems has plateaued on academic benchmarks.1 In contrast, industrial benchmarks and adoption in high-stakes domains suggest otherwise. We hypothesize that the primary difference between the two is contextual conditioning: Academic benchmarks are dominated by frequently encountered general vocabulary that is relatively easy to recognize compared with rare and context-defined custom vocabulary that has disproportionate impact on the usability of speech transcripts. Despite progress on contextual speech-to-text, there is no standardized benchmark. We introduce Contextual Earnings-22, an open dataset built upon Earnings-22, with realistic custom vocabulary contexts to foster research and reveal latent progress. We set six strong baselines for two dominant approaches: keyword prompting and keyword boosting. Experiments show both reach comparable and significantly improved accuracy when scaled from proof-of-concept to large-scale systems.

📄 PDF Abstract BibTeX arXiv:2604.07354

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Recognition

Similar Papers 제목 키워드 기반

Earnings-21: A Practical Benchmark for ASR in the Wild

2021-04-22 · Miguel Del Rio, Natalie Delworth, Ryan Westerman, Michelle Huang 외

Commonly used speech corpora inadequately challenge academic and commercial ASR systems. In particular, speech corpora lack metadata needed for detailed analysis and WER measurement. In response, we present Earnings-21, …

named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER

Earnings-22: A Practical Benchmark for Accents in the Wild

2022-03-29 · Miguel Del Rio, Peter Ha, Quinten McNamara, Corey Miller 외

Modern automatic speech recognition (ASR) systems have achieved superhuman Word Error Rate (WER) on many common corpora despite lacking adequate performance on speech in the wild. Beyond that, there is a lack of real-wor…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Benchmarkingspeech-recognition+1

Improving Contextual Recognition of Rare Words with an Alternate Spelling Prediction Model

2022-09-02 · Jennifer Drexler Fox, Natalie Delworth

Contextual ASR, which takes a list of bias terms as input along with audio, has drawn recent interest as ASR use becomes more widespread. We are releasing contextual biasing lists to accompany the Earnings21 dataset, cre…

text-to-speechText to Speech

Mobile Keyboard Input Decoding with Finite-State Transducers

2017-04-13 · Tom Ouyang, David Rybach, Françoise Beaufays, Michael Riley

We propose a finite-state transducer (FST) representation for the models used to decode keyboard inputs on mobile devices. Drawing from learnings from the field of speech recognition, we describe a decoding framework tha…

Decoderspeech-recognitionSpeech Recognition

Longer is (Not Necessarily) Stronger: Punctuated Long-Sequence Training for Enhanced Speech Recognition and Translation

2024-09-09 · Nithin Rao Koluguri, Travis Bartley, Hainan Xu, Oleksii Hrinchuk 외

This paper presents a new method for training sequence-to-sequence models for speech recognition and translation tasks. Instead of the traditional approach of training models on short segments containing only lowercase o…

speech-recognitionSpeech RecognitionTranslation