English
Related papers

Related papers: PolyIPA -- Multilingual Phoneme-to-Grapheme Conver…

200 papers

This paper describes a grapheme-to-phoneme conversion method using phoneme connectivity and CCV conversion rules. The method consists of mainly four modules including morpheme normalization, phrase-break detection, morpheme to phoneme…

cmp-lg · Computer Science 2007-05-23 Byeongchang Kim , WonIl Lee , Geunbae Lee , Jong-Hyeok Lee

Decoding attempted speech from neural activity offers a promising avenue for restoring communication abilities in individuals with speech impairments. Previous studies have focused on mapping neural activity to text using phonemes as the…

Signal Processing · Electrical Eng. & Systems 2024-11-19 Jingyuan Li , Trung Le , Chaofei Fan , Mingfei Chen , Eli Shlizerman

In this paper, we are comparing monolingual Wav2Vec 2.0 models with various multilingual models to see whether we could improve speech recognition performance on a unique oral history archive containing a lot of mixed-language sentences.…

Computation and Language · Computer Science 2024-09-26 Jan Lehečka , Josef V. Psutka , Luboš Šmídl , Pavel Ircing , Josef Psutka

This paper introduces PRobELM (Plausibility Ranking Evaluation for Language Models), a benchmark designed to assess language models' ability to discern more plausible from less plausible scenarios through their parametric knowledge. While…

Computation and Language · Computer Science 2025-04-28 Zhangdie Yuan , Eric Chamoun , Rami Aly , Chenxi Whitehouse , Andreas Vlachos

Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations. In this work…

Audio and Speech Processing · Electrical Eng. & Systems 2020-04-10 Chunxi Liu , Qiaochu Zhang , Xiaohui Zhang , Kritika Singh , Yatharth Saraf , Geoffrey Zweig

State-of-the-art speech-to-text models typically employ Transformer-based encoders that model token dependencies via self-attention mechanisms. However, the quadratic complexity of self-attention in both memory and computation imposes…

Computation and Language · Computer Science 2026-03-03 Eva Feillet , Ryan Whetten , David Picard , Alexandre Allauzen

Current state of the art acoustic models can easily comprise more than 100 million parameters. This growing complexity demands larger training datasets to maintain a decent generalization of the final decision function. An ideal dataset is…

Audio and Speech Processing · Electrical Eng. & Systems 2022-02-01 Philipp Klumpp , Tomás Arias-Vergara , Paula Andrea Pérez-Toro , Elmar Nöth , Juan Rafael Orozco-Arroyave

Allophony refers to the variation in the phonetic realization of a phoneme based on its phonetic environment. Modeling allophones is crucial for atypical pronunciation assessment, which involves distinguishing atypical from typical…

Computation and Language · Computer Science 2025-03-25 Kwanghee Choi , Eunjung Yeo , Kalvin Chang , Shinji Watanabe , David Mortensen

This paper proposes an additive phoneme-aware margin softmax (APM-Softmax) loss to train the multi-task learning network with phonetic information for language recognition. In additive margin softmax (AM-Softmax) loss, the margin is set as…

Sound · Computer Science 2021-06-25 Zheng Li , Yan Liu , Lin Li , Qingyang Hong

We introduce an approach to multilingual speech synthesis which uses the meta-learning concept of contextual parameter generation and produces natural-sounding multilingual speech using more languages and less training data than previous…

Audio and Speech Processing · Electrical Eng. & Systems 2020-08-04 Tomáš Nekvinda , Ondřej Dušek

Hindi grapheme-to-phoneme (G2P) conversion is mostly trivial, with one exception: whether a schwa represented in the orthography is pronounced or unpronounced (deleted). Previous work has attempted to predict schwa deletion in a rule-based…

Computation and Language · Computer Science 2020-04-28 Aryaman Arora , Luke Gessler , Nathan Schneider

To undertake machine lip-reading, we try to recognise speech from a visual signal. Current work often uses viseme classification supported by language models with varying degrees of success. A few recent works suggest phoneme…

Computer Vision and Pattern Recognition · Computer Science 2018-04-26 Helen L. Bear , Richard Harvey

We propose a first step toward multilingual end-to-end automatic speech recognition (ASR) by integrating knowledge about speech articulators. The key idea is to leverage a rich set of fundamental units that can be defined "universally"…

Audio and Speech Processing · Electrical Eng. & Systems 2023-09-19 Hao Yen , Sabato Marco Siniscalchi , Chin-Hui Lee

Pre-trained multilingual language models have become an important building block in multilingual natural language processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level…

Computation and Language · Computer Science 2021-06-10 Murathan Kurfalı , Robert Östling

This paper presents our segmentation system developed for the MLP 2017 shared tasks on cross-lingual word segmentation and morpheme segmentation. We model both word and morpheme segmentation as character-level sequence labelling tasks. The…

Computation and Language · Computer Science 2017-09-13 Yan Shao

We propose a model to obtain phonemic and prosodic labels of speech that are coherent with graphemes. Unlike previous methods that simply fine-tune a pre-trained ASR model with the labels, the proposed model conditions the label generation…

Sound · Computer Science 2025-06-06 Hien Ohnaka , Yuma Shirahata , Byeongseon Park , Ryuichi Yamamoto

Language modeling has witnessed remarkable advancements in recent years, with Large Language Models (LLMs) like ChatGPT setting unparalleled benchmarks in human-like text generation. However, a prevailing limitation is the…

Computation and Language · Computer Science 2023-11-13 Abhinand Balachandran

We propose a novel morphologically aware probability model for bilingual lexicon induction, which jointly models lexeme translation and inflectional morphology in a structured way. Our model exploits the basic linguistic intuition that the…

Computation and Language · Computer Science 2020-11-17 Paula Czarnowska , Sebastian Ruder , Ryan Cotterell , Ann Copestake

Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without…

Audio and Speech Processing · Electrical Eng. & Systems 2026-05-25 Jazmín Vidal , Luciana Ferrer

It is challenging to build a multi-singer high-fidelity singing voice synthesis system with cross-lingual ability by only using monolingual singers in the training stage. In this paper, we propose CrossSinger, which is a cross-lingual…

Sound · Computer Science 2023-09-25 Xintong Wang , Chang Zeng , Jun Chen , Chunhui Wang