Related papers: Weakly-supervised word-level pronunciation error d…

Child speech recognition is still an underdeveloped area of research due to the lack of data (especially on non-English languages) and the specific difficulties of this task. Having explored various architectures for child speech…

Speech evaluation measures a learners oral proficiency using automatic models. Corpora for training such models often pose sparsity challenges given that there often is limited scored data from teachers, in addition to the score…

Detecting medical conditions from speech acoustics is fundamentally a weakly-supervised learning problem: a single, often noisy, session-level label must be linked to nuanced patterns within a long, complex audio recording. This task is…

The goal of this paper is to learn strong lip reading models that can recognise speech in silent videos. Most prior works deal with the open-set visual speech recognition problem by adapting existing automatic speech recognition techniques…

Evaluating speech intelligibility is a critical task in computer-aided language learning systems. Traditional methods often rely on word error rates (WER) provided by automatic speech recognition (ASR) as intelligibility scores. However,…

Modern language models mostly take sub-words as input, a design that balances the trade-off between vocabulary size, number of parameters, and performance. However, sub-word tokenization still has disadvantages like not being robust to…

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 spoken language assessment systems are becoming more popular in order to handle increasing interests in second language learning. One challenge for these systems is to detect malpractice. Malpractice can take a range of forms,…

In this paper, we extend previous self-supervised approaches for language identification by experimenting with Conformer based architecture in a multilingual pre-training paradigm. We find that pre-trained speech models optimally encode…

Weakly-supervised semantic parsers are trained on utterance-denotation pairs, treating logical forms as latent. The task is challenging due to the large search space and spuriousness of logical forms. In this paper we introduce a neural…

We introduce a data-driven approach for enabling word-level timestamp prediction in the Canary model. Accurate timestamp information is crucial for a variety of downstream tasks such as speech content retrieval and timed subtitles. While…

This paper presents a novel approach for multi-lingual sentiment classification in short texts. This is a challenging task as the amount of training data in languages other than English is very limited. Previously proposed multi-lingual…

This paper presents a new approach for unsupervised Spoken Term Detection with spoken queries using multiple sets of acoustic patterns automatically discovered from the target corpus. The different pattern HMM configurations(number of…

Recently in speaker recognition, performance degradation due to the channel domain mismatched condition has been actively addressed. However, the mismatches arising from language is yet to be sufficiently addressed. This paper proposes an…

Techniques for unsupervised discovery of acoustic patterns are getting increasingly attractive, because huge quantities of speech data are becoming available but manual annotations remain hard to acquire. In this paper, we propose an…

Mismatched transcriptions have been proposed as a mean to acquire probabilistic transcriptions from non-native speakers of a language.Prior work has demonstrated the value of these transcriptions by successfully adapting cross-lingual ASR…

Neural language models (LMs) are typically trained using only lexical features, such as surface forms of words. In this paper, we argue this deprives the LM of crucial syntactic signals that can be detected at high confidence using existing…

In conventional supervised pattern recognition tasks, model selection is typically accomplished by minimizing the classification error rate on a set of so-called development data, subject to ground-truth labeling by human experts or some…

Self-supervised pre-trained speech models have strongly improved speech recognition, yet they are still sensitive to domain shifts and accented or atypical speech. Many of these models rely on quantisation or clustering to learn discrete…

This paper investigates different pretraining approaches to spoken language identification. The paper is based on our submission to the Oriental Language Recognition 2021 Challenge. We participated in two tracks of the challenge:…