paper-with-me

홈 › Papers

Spoken Term Detection Methods for Sparse Transcription in Very Low-resource Settings

2021-06-11 · Éric Le Ferrand, Steven Bird, Laurent Besacier

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust ASR system. This work is grounded in very low-resource language documentation scenario where only few minutes of recording have been transcribed for a given language so far.Experiments on two oral languages show that a pretrained universal phone recognizer, fine-tuned with only a few minutes of target language speech, can be used for spoken term detection with a better overall performance than a dynamic time warping approach. In addition, we show that representing phoneme recognition ambiguity in a graph structure can further boost the recall while maintaining high precision in the low resource spoken term detection task.

📄 PDF Abstract BibTeX arXiv:2106.06160

Code (0)

등록된 구현이 없습니다.

Tasks

Dynamic Time WarpingPhoneme Recognition

Similar Papers 제목 키워드 기반

Sparse Transcription

2020-12-01 · CL (ACL) 2020 12 · Steven Bird

The transcription bottleneck is often cited as a major obstacle for efforts to document the world’s endangered languages and supply them with language technologies. One solution is to extend methods from automatic speech…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Machine TranslationSentence+3

Enabling Interactive Transcription in an Indigenous Community

2020-11-12 · COLING 2020 8 · Éric Le Ferrand, Steven Bird, Laurent Besacier

We propose a novel transcription workflow which combines spoken term detection and human-in-the-loop, together with a pilot experiment. This work is grounded in an almost zero-resource scenario where only a few terms hav…

H-QuEST: Accelerating Query-by-Example Spoken Term Detection with Hierarchical Indexing

2025-06-20 · Akanksha Singh, Yi-Ping Phoebe Chen, Vipul Arora

Query-by-example spoken term detection (QbE-STD) searches for matching words or phrases in an audio dataset using a sample spoken query. When annotated data is limited or unavailable, QbE-STD is often done using template…

Dynamic Time WarpingRepresentation LearningRetrievalTemplate Matching

Phone Based Keyword Spotting for Transcribing Very Low Resource Languages

2021-12-01 · ALTA 2021 12 · Eric Le Ferrand, Steven Bird, Laurent Besacier

We investigate the efficiency of two very different spoken term detection approaches for transcription when the available data is insufficient to train a robust speech recognition system. This work is grounded in a very …

Dynamic Time WarpingKeyword SpottingRobust Speech Recognitionspeech-recognition+1

Grammatical error detection in transcriptions of spoken English

2020-12-01 · COLING 2020 8 · Andrew Caines, Christian Bentz, Kate Knill, Marek Rei 외

We describe the collection of transcription corrections and grammatical error annotations for the CrowdED Corpus of spoken English monologues on business topics. The corpus recordings were crowdsourced from native speake…

Grammatical Error CorrectionGrammatical Error Detection