Related papers: A Two-Step Approach for Data-Efficient French Pron…

Macroeconomic data are crucial for monitoring countries' performance and driving policy. However, traditional data acquisition processes are slow, subject to delays, and performed at a low frequency. We address this 'ragged-edge' problem…

Homograph disambiguation remains a significant challenge in grapheme-to-phoneme (G2P) conversion, especially for low-resource languages. This challenge is twofold: (1) creating balanced and comprehensive homograph datasets is…

The potential of synthetic data in text-to-speech (TTS) model training has gained increasing attention, yet its rationality and effectiveness require systematic validation. In this study, we systematically investigate the feasibility of…

Recent progress in Spoken Language Modeling has shown that learning language directly from speech is feasible. Generating speech through a pipeline that operates at the text level typically loses nuances, intonations, and non-verbal…

This paper describes a new unsupervised machine learning method for simultaneous phoneme and word discovery from multiple speakers. Human infants can acquire knowledge of phonemes and words from interactions with his/her mother as well as…

Graph-based semi-supervised learning has proven to be an effective approach for query-focused multi-document summarization. The problem of previous semi-supervised learning is that sentences are ranked without considering the higher level…

This paper presents PolyIPA, a novel multilingual phoneme-to-grapheme conversion model designed for multilingual name transliteration, onomastic research, and information retrieval. The model leverages two helper models developed for data…

*Data Synthesis* is a promising way to train a small model with very little labeled data. One approach for data synthesis is to leverage the rich knowledge from large language models to synthesize pseudo training examples for small models,…

Language documentation is inherently a time-intensive process; transcription, glossing, and corpus management consume a significant portion of documentary linguists' work. Advances in natural language processing can help to accelerate this…

In this paper, we present how to hybridize a Word2vec model and an attention-based end-to-end speech recognition model. We build a phoneme recognition system based on Listen, Attend and Spell model. And the phoneme recognition model uses a…

In the domain of unsupervised learning most work on speech has focused on discovering low-level constructs such as phoneme inventories or word-like units. In contrast, for written language, where there is a large body of work on…

This article reports the evaluation of the integration of data from a syntactic-semantic lexicon, the Lexicon-Grammar of French, into a syntactic parser. We show that by changing the set of labels for verbs and predicational nouns, we can…

We propose a method to perform audio event detection under the common constraint that only limited training data are available. In training a deep learning system to perform audio event detection, two practical problems arise. Firstly, most…

This paper explores the challenges of test-time scaling of large language models (LLMs), regarding both the data and inference efficiency. We highlight the diversity of multi-lingual reasoning based on our pilot studies, and then introduce…

Whereas conventional spoken language understanding (SLU) systems map speech to text, and then text to intent, end-to-end SLU systems map speech directly to intent through a single trainable model. Achieving high accuracy with these…

In this paper, we present a data set and methods to compare speech processing models and human behaviour on a phone discrimination task. We provide Perceptimatic, an open data set which consists of French and English speech stimuli, as well…

Existing fake audio detection systems perform well in in-domain testing, but still face many challenges in out-of-domain testing. This is due to the mismatch between the training and test data, as well as the poor generalizability of…

Automatic pronunciation assessment is a major component of a computer-assisted pronunciation training system. To provide in-depth feedback, scoring pronunciation at various levels of granularity such as phoneme, word, and utterance, with…

Active learning aims to reduce labeling efforts by selectively asking humans to annotate the most important data points from an unlabeled pool and is an example of human-machine interaction. Though active learning has been extensively…

In recent years, new developments in the area of lexicography have altered not only the management, processing and publishing of lexicographical data, but also created new types of products such as electronic dictionaries and thesauri.…