Related papers: A Swiss German Dictionary: Variation in Speech and…
Neural language models trained with a predictive or masked objective have proven successful at capturing short and long distance syntactic dependencies. Here, we focus on verb argument structure in German, which has the interesting property…
Machine transliteration is a method for automatically converting words in one language into phonetically equivalent ones in another language. Machine transliteration plays an important role in natural language applications such as…
Segmentation remains an important preprocessing step both in languages where "words" or other important syntactic/semantic units (like morphemes) are not clearly delineated by white space, as well as when dealing with continuous speech…
This research optimizes two-pass cross-lingual transfer learning in low-resource languages by enhancing phoneme recognition and phoneme-to-grapheme translation models. Our approach optimizes these two stages to improve speech recognition…
This work proposes Adaptive Facilitated Mutation, a self-adaptive mutation method for Structured Grammatical Evolution (SGE), biologically inspired by the theory of facilitated variation. In SGE, the genotype of individuals contains a list…
In this article, we present an approach for non native automatic speech recognition (ASR). We propose two methods to adapt existing ASR systems to the non-native accents. The first method is based on the modification of acoustic models…
Cross-linguistically, native words and loanwords follow different phonological rules. In English, for example, words of Germanic and Latinate origin exhibit different stress patterns, and a certain syntactic structure, double-object…
In recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised…
Recent advances in spoken language processing have led to substantial progress in phonetic tasks such as automatic speech recognition (ASR), phone recognition (PR), grapheme-to-phoneme conversion (G2P), and phoneme-to-grapheme conversion…
We introduce the notion of a subgraph generated by an $R$-word $r$ of the Sch\"{u}tzenberger graph of a positive word $w$, $S\Gamma(w)$, where $w$ contains $r$ as its subword. We show that the word problem for a finitely presented Adian…
Automatic speech recognition is a difficult problem in pattern recognition because several sources of variability exist in the speech input like the channel variations, the input might be clean or noisy, the speakers may have different…
Languages vary widely in how meanings map to word forms. These mappings have been found to support efficient communication; however, this theory does not account for systematic relations within word forms. We examine how a restricted set of…
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…
A phonetic posteriorgram (PPG) is a time-varying categorical distribution over acoustic units of speech (e.g., phonemes). PPGs are a popular representation in speech generation due to their ability to disentangle pronunciation features from…
We analyze the influence of utterance-level construction distributions in German child-directed/child-available speech on the resulting word-level, syntactic and semantic competence (and their underlying learning trajectories) in small LMs,…
In this paper, we propose three methods for generating synthetic samples to train and evaluate multimodal large language models capable of processing both text and speech inputs. Addressing the scarcity of samples containing both…
Natural language generation models reproduce and often amplify the biases present in their training data. Previous research explored using sequence-to-sequence rewriting models to transform biased model outputs (or original texts) into more…
Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…
Skip-gram (word2vec) is a recent method for creating vector representations of words ("distributed word representations") using a neural network. The representation gained popularity in various areas of natural language processing, because…
Alzheimer's Disease is the most common form of dementia. Automatic detection from speech could help to identify symptoms at early stages, so that preventive actions can be carried out. This research is a contribution to the ADReSSo…