Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs
- URL: http://arxiv.org/abs/2501.05234v1
- Date: Thu, 09 Jan 2025 13:41:37 GMT
- Title: Optimizing Estonian TV Subtitles with Semi-supervised Learning and LLMs
- Authors: Artem Fedorchenko, Tanel Alumäe,
- Abstract summary: We fine-tune the Whisper model on human-generated Estonian subtitles and enhance it with iterative pseudo-labeling and large language model (LLM) based post-editing.
Experiments demonstrate notable subtitle quality improvement through pseudo-labeling with an unlabeled dataset.
- Score: 4.297070083645049
- License:
- Abstract: This paper presents an approach for generating high-quality, same-language subtitles for Estonian TV content. We fine-tune the Whisper model on human-generated Estonian subtitles and enhance it with iterative pseudo-labeling and large language model (LLM) based post-editing. Our experiments demonstrate notable subtitle quality improvement through pseudo-labeling with an unlabeled dataset. We find that applying LLM-based editing at test time enhances subtitle accuracy, while its use during training does not yield further gains. This approach holds promise for creating subtitle quality close to human standard and could be extended to real-time applications.
Related papers
- Improving Text-To-Audio Models with Synthetic Captions [51.19111942748637]
We propose an audio captioning pipeline that uses an textitaudio language model to synthesize accurate and diverse captions for audio at scale.
We leverage this pipeline to produce a dataset of synthetic captions for AudioSet, named textttAF-AudioSet, and then evaluate the benefit of pre-training text-to-audio models on these synthetic captions.
arXiv Detail & Related papers (2024-06-18T00:02:15Z) - HowToCaption: Prompting LLMs to Transform Video Annotations at Scale [72.69268311756082]
We propose to leverage the capabilities of large language models (LLMs) to obtain high-quality video descriptions aligned with videos at scale.
We introduce a prompting method that is able to take into account a longer text of subtitles, allowing us to capture the contextual information beyond one single sentence.
We apply our method to the subtitles of the HowTo100M dataset, creating a new large-scale dataset, HowToCaption.
arXiv Detail & Related papers (2023-10-07T19:32:55Z) - Gloss Alignment Using Word Embeddings [40.100782464872076]
We propose a method for aligning spottings with their corresponding subtitles using large spoken language models.
We quantitatively demonstrate the effectiveness of our method on the acfmdgs and acfbobsl datasets.
arXiv Detail & Related papers (2023-08-08T13:26:53Z) - CLIPSonic: Text-to-Audio Synthesis with Unlabeled Videos and Pretrained
Language-Vision Models [50.42886595228255]
We propose to learn the desired text-audio correspondence by leveraging the visual modality as a bridge.
We train a conditional diffusion model to generate the audio track of a video, given a video frame encoded by a pretrained contrastive language-image pretraining model.
arXiv Detail & Related papers (2023-06-16T05:42:01Z) - Automatic dense annotation of large-vocabulary sign language videos [85.61513254261523]
We propose a simple, scalable framework to vastly increase the density of automatic annotations.
We make these annotations publicly available to support the sign language research community.
arXiv Detail & Related papers (2022-08-04T17:55:09Z) - Between Flexibility and Consistency: Joint Generation of Captions and
Subtitles [13.58711830450618]
Speech translation (ST) has lately received growing interest for the generation of subtitles without the need for an intermediate source language transcription and timing.
In this work, we focus on ST models which generate consistent captions-subtitles in terms of structure and lexical content.
Our findings show that joint decoding leads to increased performance and consistency between the generated captions and subtitles while still allowing for sufficient flexibility to produce subtitles conforming to language-specific needs and norms.
arXiv Detail & Related papers (2021-07-13T17:06:04Z) - Aligning Subtitles in Sign Language Videos [80.20961722170655]
We train on manually annotated alignments covering over 15K subtitles that span 17.7 hours of video.
We use BERT subtitle embeddings and CNN video representations learned for sign recognition to encode the two signals.
Our model outputs frame-level predictions, i.e., for each video frame, whether it belongs to the queried subtitle or not.
arXiv Detail & Related papers (2021-05-06T17:59:36Z) - Watch and Learn: Mapping Language and Noisy Real-world Videos with
Self-supervision [54.73758942064708]
We teach machines to understand visuals and natural language by learning the mapping between sentences and noisy video snippets without explicit annotations.
For training and evaluation, we contribute a new dataset ApartmenTour' that contains a large number of online videos and subtitles.
arXiv Detail & Related papers (2020-11-19T03:43:56Z) - MuST-Cinema: a Speech-to-Subtitles corpus [16.070428245677675]
We present MuST-Cinema, a multilingual speech translation corpus built from TED subtitles.
We show that the corpus can be used to build models that efficiently segment sentences into subtitles.
We propose a method for annotating existing subtitling corpora with subtitle breaks, conforming to the constraint of length.
arXiv Detail & Related papers (2020-02-25T12:40:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.