paper-with-me

홈 › Papers

InterBiasing: Boost Unseen Word Recognition through Biasing Intermediate Predictions

2024-06-21 · Yu Nakagome, Michael Hentschel

Despite recent advances in end-to-end speech recognition methods, their output is biased to the training data's vocabulary, resulting in inaccurate recognition of unknown terms or proper nouns. To improve the recognition accuracy for a given set of such terms, we propose an adaptation parameter-free approach based on Self-conditioned CTC. Our method improves the recognition accuracy of misrecognized target keywords by substituting their intermediate CTC predictions with corrected labels, which are then passed on to the subsequent layers. First, we create pairs of correct labels and recognition error instances for a keyword list using Text-to-Speech and a recognition model. We use these pairs to replace intermediate prediction errors by the labels. Conditioning the subsequent layers of the encoder on the labels, it is possible to acoustically evaluate the target keywords. Experiments conducted in Japanese demonstrated that our method successfully improved the F1 score for unknown words.

📄 PDF Abstract BibTeX arXiv:2406.14890

Code (0)

등록된 구현이 없습니다.

Tasks

speech-recognitionSpeech Recognitiontext-to-speechText to Speech

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Spell my name: keyword boosted speech recognition

2021-10-06 · Namkyu Jung, Geonmin Kim, Joon Son Chung

Recognition of uncommon words such as names and technical terminology is important to understanding conversations in context. However, the ability to recognise such words remains a challenge in modern automatic speech re…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine Translationspeech-recognition+2

Improving Rare-Word Recognition of Whisper in Zero-Shot Settings

2025-02-17 · Yash Jogi, Vaibhav Aggarwal, Shabari S Nair, Yash Verma 외

Whisper, despite being trained on 680K hours of web-scaled audio data, faces difficulty in recognising rare words like domain-specific terms, with a solution being contextual biasing through prompting. To improve upon th…

Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition

2019-03-30 · Jingcai Guo, Song Guo

In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classe…

Zero-Shot Learning

Deep word embeddings for visual speech recognition

2017-10-30 · Themos Stafylakis, Georgios Tzimiropoulos

In this paper we present a deep learning architecture for extracting word embeddings for visual speech recognition. The embeddings summarize the information of the mouth region that is relevant to the problem of word rec…

Lipreadingspeech-recognitionSpeech RecognitionVisual Speech Recognition+1

Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition

2020-08-10

Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech r…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DiversityMachine Translation+4