paper-with-me

홈 › Papers

Syllable Subword Tokens for Open Vocabulary Speech Recognition in Malayalam

2023-01-17 · Kavya Manohar, A. R. Jayan, Rajeev Rajan

In a hybrid automatic speech recognition (ASR) system, a pronunciation lexicon (PL) and a language model (LM) are essential to correctly retrieve spoken word sequences. Being a morphologically complex language, the vocabulary of Malayalam is so huge and it is impossible to build a PL and an LM that cover all diverse word forms. Usage of subword tokens to build PL and LM, and combining them to form words after decoding, enables the recovery of many out of vocabulary words. In this work we investigate the impact of using syllables as subword tokens instead of words in Malayalam ASR, and evaluate the relative improvement in lexicon size, model memory requirement and word error rate.

📄 PDF Abstract BibTeX arXiv:2301.06736

Code (1)

https://gitlab.com/kavyamanohar/ml-subword-asr 공식 구현

Tasks

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition

Similar Papers 제목 키워드 기반

Revisiting Neural Language Modelling with Syllables

2020-10-24 · Arturo Oncevay, Kervy Rivas Rojas

Language modelling is regularly analysed at word, subword or character units, but syllables are seldom used. Syllables provide shorter sequences than characters, they can be extracted with rules, and their segmentation t…

Language Modelling

Revisiting Syllables in Language Modelling and their Application on Low-Resource Machine Translation

2022-10-05 · COLING 2022 10 · Arturo Oncevay, Kervy Dante Rivas Rojas, Liz Karen Chavez Sanchez, Roberto Zariquiey

Language modelling and machine translation tasks mostly use subword or character inputs, but syllables are seldom used. Syllables provide shorter sequences than characters, require less-specialised extracting rules than …

Language ModellingMachine TranslationSegmentationTranslation

Automatic Transcription Challenges for Inuktitut, a Low-Resource Polysynthetic Language

2020-05-01 · LREC 2020 5 · Vishwa Gupta, Gilles Boulianne

We introduce the first attempt at automatic speech recognition (ASR) in Inuktitut, as a representative for polysynthetic, low-resource languages, like many of the 900 Indigenous languages spoken in the Americas. As most …

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

Contextualized Automatic Speech Recognition with Dynamic Vocabulary

2024-05-22 · Yui Sudo, Yosuke Fukumoto, Muhammad Shakeel, Yifan Peng 외

Deep biasing (DB) enhances the performance of end-to-end automatic speech recognition (E2E-ASR) models for rare words or contextual phrases using a bias list. However, most existing methods treat bias phrases as sequence…

Automatic Speech RecognitionLanguage ModelingLanguage Modellingspeech-recognition+1

Mlphon: A Multifunctional Grapheme-Phoneme Conversion Tool Using Finite State Transducers

2022-09-05 · IEEE Access 2022 9 · Kavya Manohar, A R jayan, Rajeev Rajan

In this article we present the design and the development of a knowledge based computational linguistic tool, Mlphon for Malayalam language. Mlphon computationally models linguistic rules using finite state transducers a…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)DiversityGrapheme-to-Phoneme Conversion+10