paper-with-me

홈 › Papers

Streaming Punctuation for Long-form Dictation with Transformers

2022-10-11 · Piyush Behre, Sharman Tan, Padma Varadharajan, Shuangyu Chang

While speech recognition Word Error Rate (WER) has reached human parity for English, long-form dictation scenarios still suffer from segmentation and punctuation problems resulting from irregular pausing patterns or slow speakers. Transformer sequence tagging models are effective at capturing long bi-directional context, which is crucial for automatic punctuation. Automatic Speech Recognition (ASR) production systems, however, are constrained by real-time requirements, making it hard to incorporate the right context when making punctuation decisions. In this paper, we propose a streaming approach for punctuation or re-punctuation of ASR output using dynamic decoding windows and measure its impact on punctuation and segmentation accuracy across scenarios. The new system tackles over-segmentation issues, improving segmentation F0.5-score by 13.9%. Streaming punctuation achieves an average BLEU-score improvement of 0.66 for the downstream task of Machine Translation (MT).

📄 PDF Abstract BibTeX arXiv:2210.05756

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)FormMachine TranslationSegmentationspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Robust Prediction of Punctuation and Truecasing for Medical ASR

2020-07-04 · WS 2020 7 · Monica Sunkara, Srikanth Ronanki, Kalpit Dixit, Sravan Bodapati 외

Automatic speech recognition (ASR) systems in the medical domain that focus on transcribing clinical dictations and doctor-patient conversations often pose many challenges due to the complexity of the domain. ASR output …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Data AugmentationPrediction+2

A Small and Fast BERT for Chinese Medical Punctuation Restoration

2023-08-24 · Tongtao Ling, Yutao Lai, Lei Chen, Shilei Huang 외

In clinical dictation, utterances after automatic speech recognition (ASR) without explicit punctuation marks may lead to the misunderstanding of dictated reports. To give a precise and understandable clinical report wit…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Contrastive LearningPunctuation Restoration+2

Streaming Punctuation: A Novel Punctuation Technique Leveraging Bidirectional Context for Continuous Speech Recognition

2023-01-10 · Piyush Behre, Sharman Tan, Padma Varadharajan, Shuangyu Chang

While speech recognition Word Error Rate (WER) has reached human parity for English, continuous speech recognition scenarios such as voice typing and meeting transcriptions still suffer from segmentation and punctuation …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationSegmentation+2

Deep Learning for Punctuation Restoration in Medical Reports

2017-08-01 · WS 2017 8 · Wael Salloum, Greg Finley, Erik Edwards, Mark Miller 외

In clinical dictation, speakers try to be as concise as possible to save time, often resulting in utterances without explicit punctuation commands. Since the end product of a dictated report, e.g. an out-patient letter, …

Deep LearningPunctuation RestorationSpeech Recognition

Improved Training for End-to-End Streaming Automatic Speech Recognition Model with Punctuation

2023-06-02 · Hanbyul Kim, Seunghyun Seo, Lukas Lee, Seolki Baek

Punctuated text prediction is crucial for automatic speech recognition as it enhances readability and impacts downstream natural language processing tasks. In streaming scenarios, the ability to predict punctuation in re…

Automatic Speech Recognitionspeech-recognitionSpeech Recognition