Improving recognition of proper nouns in ASR through generating and filtering phonetic transcriptions

Laurent, Antoine; Meignier, Sylvain; Deléglise, Paul

doi:10.1016/j.csl.2014.02.006

Cited by 8 publications

(5 citation statements)

References 24 publications

(32 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AER is used as a metric for the entire system assessment. Inspired by WER [9], AER measures the minimum number of operations, i.e., substitutions, deletions, and insertions, to make a word under evaluation match the reference. The AER is calculated as follows:…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Automatic Thai Finger Spelling Transcription

Nakjai

Katanyukul

2021

Walailak J Sci & Tech

View full text Add to dashboard Cite

This article explores a transcription of a video recording Thai Finger Spelling (TFS)—a specific signing mode used in Thai sign language—to a corresponding Thai word. TFS copes with 42 Thai alphabets and 20 vowels using multiple and complex schemes. This leads to many technical challenges uncommon in spelling schemes of other sign languages. Our proposed system, Automatic Thai Finger Spelling Transcription (ATFS), processes a signing video in 3 stages: ALS marking video frames to easily remove any non-signing frame as well as conveniently group frames associating to the same alphabet, SR classifying a signing image frame to a sign label (or its equivalence), and SSR transcribing a series of signs into alphabets. ALS utilizes the TFS practice of signing different alphabets at different locations. SR and SSC employ well-adopted spatial and sequential models. Our ATFS has been found to achieve Alphabet Error Rate (AER) 0.256 (c.f. 0.63 of the baseline method). In addition to ATFS, our findings have disclosed a benefit of coupling image classification and sequence modeling stages by using a feature or penultimate vector for label representation rather than a definitive label or one-hot coding. Our results also assert the necessity of a smoothening mechanism in ALS and reveal a benefit of our proposed WFS, which could lead to over 15.88 % improvement. For TFS transcription, our work emphasizes the utilization of signing location in the identification of different alphabets. This is contrary to a common belief of exploiting signing time duration, which are shown to be ineffective by our data. HIGHLIGHTS Prototype of Thai finger spelling transcription (transcribing a signing video to alphabets) Utilization of signing location as cue for identification of different alphabets Disclosure of a benefit of coupling image classification and sequence modeling in signing transcription Examination of various frame smoothing techniques and their contributions to the overall transcription performance GRAPHICAL ABSTRACT

show abstract

Section: Discussionmentioning

confidence: 99%

“…This finding may help bring awareness when a pipeline is designed. Regarding the evaluation of the transcription, we adopt a concept of Word Error Rate (WER) [9] to propose AER for the overall performance index.…”

Section: Automatic Thai Finger Spelling Transcriptionmentioning

confidence: 99%

Automatic Thai Finger Spelling Transcription

Nakjai

Katanyukul

2021

Walailak J Sci & Tech

View full text Add to dashboard Cite

show abstract

“…The conversion process needs rules or learning from the seed data given during the process. The data-driven approach derives the pronunciation data from the seed data (Laurent et al, 2014). This study focuses on data-driven modelling techniques, which will be explained further in Data-Driven G2P techniques.…”

Section: Grapheme-to-phoneme Conversionmentioning

confidence: 99%

A Review on Grapheme-to-Phoneme Modelling Techniques to Transcribe Pronunciation Variants for Under-Resourced Language

Irie¹,

Juan²,

Saee³

2023

JST

View full text Add to dashboard Cite

A pronunciation dictionary (PD) is one of the components in an Automatic Speech Recognition (ASR) system, a system that is used to convert speech to text. The dictionary consists of word-phoneme pairs that map sound units to phonetic units for modelling and predictions. Research has shown that words can be transcribed to phoneme sequences using grapheme-to-phoneme (G2P) models, which could expedite building PDs. The G2P models can be developed by training seed PD data using statistical approaches requiring large amounts of data. Consequently, building PD for under-resourced languages is a great challenge due to poor grapheme and phoneme systems in these languages. Moreover, some PDs must include pronunciation variants, including regional accents that native speakers practice. For example, recent work on a pronunciation dictionary for an ASR in Iban, an under-resourced language from Malaysia, was built through a bootstrapping G2P method. However, the current Iban pronunciation dictionary has yet to include pronunciation variants that the Ibans practice. Researchers have done recent studies on Iban pronunciation variants, but no computational methods for generating the variants are available yet. Thus, this paper reviews G2P algorithms and processes we would use to develop pronunciation variants automatically. Specifically, we discuss data-driven techniques such as CRF, JSM, and JMM. These methods were used to build PDs for Thai, Arabic, Tunisian, and Swiss-German languages. Moreover, this paper also highlights the importance of pronunciation variants and how they can affect ASR performance.

show abstract

“…Proper nouns have been identified as a challenging problem in ASR for a while now [4]. Recently some approaches have arisen to tackle this challenge with E2E ASR using a specialised architecture and losses [5] or using specific data and training procedures to better represent contextual information [6].…”

Section: Introductionmentioning

confidence: 99%

Meta-Learning for Improving Rare Word Recognition in End-to-End ASR

Lux

2021

ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

In this work we take on the challenge of rare word recognition in endto-end (E2E) automatic speech recognition (ASR) by integrating a meta learning mechanism into an E2E ASR system, enabling few-shot adaptation. We propose a novel method of generating embeddings for speech, changes to four meta learning approaches, enabling them to perform keyword spotting and an approach to using their outcomes in an E2E ASR system. We verify the functionality of each of our three contributions in two experiments exploring their performance for different amounts of classes (N-way) and examples per class (k-shot) in a few-shot setting. We find that the information encoded in the speech embeddings suffices to allow the modified meta learning approaches to perform continuous signal spotting. Despite the simplicity of the interface between keyword spotting and speech recognition, we are able to consistently improve word error rate by up to 5%.

show abstract

Improving recognition of proper nouns in ASR through generating and filtering phonetic transcriptions

Cited by 8 publications

References 24 publications

Automatic Thai Finger Spelling Transcription

Automatic Thai Finger Spelling Transcription

A Review on Grapheme-to-Phoneme Modelling Techniques to Transcribe Pronunciation Variants for Under-Resourced Language

Meta-Learning for Improving Rare Word Recognition in End-to-End ASR

Contact Info

Product

Resources

About