paper-with-me

홈 › Papers

Learning to Jointly Transcribe and Subtitle for End-to-End Spontaneous Speech Recognition

2022-10-14 · Jakob Poncelet, Hugo Van hamme

TV subtitles are a rich source of transcriptions of many types of speech, ranging from read speech in news reports to conversational and spontaneous speech in talk shows and soaps. However, subtitles are not verbatim (i.e. exact) transcriptions of speech, so they cannot be used directly to improve an Automatic Speech Recognition (ASR) model. We propose a multitask dual-decoder Transformer model that jointly performs ASR and automatic subtitling. The ASR decoder (possibly pre-trained) predicts the verbatim output and the subtitle decoder generates a subtitle, while sharing the encoder. The two decoders can be independent or connected. The model is trained to perform both tasks jointly, and is able to effectively use subtitle data. We show improvements on regular ASR and on spontaneous and conversational ASR by incorporating the additional subtitle decoder. The method does not require preprocessing (aligning, filtering, pseudo-labeling, ...) of the subtitles.

📄 PDF Abstract BibTeX arXiv:2210.07771

Code (0)

등록된 구현이 없습니다.

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Decoderspeech-recognitionSpeech Recognition

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
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…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Leveraging Broadcast Media Subtitle Transcripts for Automatic Speech Recognition and Subtitling

2025-02-05 · Jakob Poncelet, Hugo Van hamme

The recent advancement of speech recognition technology has been driven by large-scale datasets and attention-based architectures, but many challenges still remain, especially for low-resource languages and dialects. Thi…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Bringing NURC/SP to Digital Life: the Role of Open-source Automatic Speech Recognition Models

2022-10-14 · Lucas Rafael Stefanel Gris, Arnaldo Candido Junior, Vinícius G. dos Santos, Bruno A. Papa Dias 외

The NURC Project that started in 1969 to study the cultured linguistic urban norm spoken in five Brazilian capitals, was responsible for compiling a large corpus for each capital. The digitized NURC/SP comprises 375 inqu…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

TUKE-BNews-SK: Slovak Broadcast News Corpus Construction and Evaluation

2014-05-01 · LREC 2014 5 · Mat{\'u}{\v{s}} Pleva, Jozef Juh{\'a}r

This article presents an overview of the existing acoustical corpuses suitable for broadcast news automatic transcription task in the Slovak language. The TUKE-BNews-SK database created in our department was built to sup…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

Construction of a Large-scale Japanese ASR Corpus on TV Recordings

2021-03-26 · Shintaro Ando, Hiromasa Fujihara

This paper presents a new large-scale Japanese speech corpus for training automatic speech recognition (ASR) systems. This corpus contains over 2,000 hours of speech with transcripts built on Japanese TV recordings and t…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

GigaSpeech: An Evolving, Multi-domain ASR Corpus with 10,000 Hours of Transcribed Audio

2021-06-13 · Guoguo Chen, Shuzhou Chai, Guanbo Wang, Jiayu Du 외

This paper introduces GigaSpeech, an evolving, multi-domain English speech recognition corpus with 10,000 hours of high quality labeled audio suitable for supervised training, and 40,000 hours of total audio suitable for…

Sentencespeech-recognitionSpeech Recognition