Related papers: Quantity Convergence, Quality Divergence: Disentan…
In Mandarin, the tonal contours of monosyllabic words produced in isolation or in careful speech are characterized by four lexical tones: a high-level tone (T1), a rising tone (T2), a dipping tone (T3) and a falling tone (T4). However, in…
Recent studies in speech perception have been closely linked to fields of cognitive psychology, phonology, and phonetics in linguistics. During perceptual attunement, a critical and sensitive developmental trajectory has been examined in…
Contextualized end-to-end automatic speech recognition has been an active research area, with recent efforts focusing on the implicit learning of contextual phrases based on the final loss objective. However, these approaches ignore the…
Prosody is essential for speech technology, shaping comprehension, naturalness, and expressiveness. However, current text-to-speech (TTS) systems still struggle to accurately capture human-like prosodic variation, in part because existing…
Dialogue-level dependency parsing has received insufficient attention, especially for Chinese. To this end, we draw on ideas from syntactic dependency and rhetorical structure theory (RST), developing a high-quality human-annotated corpus,…
This paper proposes an Expressive Speech Synthesis model that utilizes token-level latent prosodic variables in order to capture and control utterance-level attributes, such as character acting voice and speaking style. Current works aim to…
We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks,…
Spoken languages show significant variation across mandarin and accent. Despite the high performance of mandarin automatic speech recognition (ASR), accent ASR is still a challenge task. In this paper, we introduce meta-learning techniques…
Despite their remarkable ability to capture linguistic nuances across diverse languages, questions persist regarding the degree of alignment between languages in multilingual embeddings. Drawing inspiration from research on high-dimensional…
Vector comparison in high dimensions is a fundamental task in NLP, yet it is dominated by two baselines: the raw dot product, which is unbounded and sensitive to vector norms, and the cosine similarity, which discards magnitude information…
Cantonese, although spoken by millions, remains under-resourced due to policy and diglossia. To address this scarcity of evaluation frameworks for Cantonese, we introduce \textsc{\textbf{CantoNLU}}, a benchmark for Cantonese natural…
Recent state-of-the-art neural text-to-speech (TTS) synthesis models have dramatically improved intelligibility and naturalness of generated speech from text. However, building a good bilingual or code-switched TTS for a particular voice is…
Despite the impressive growth of the abilities of multilingual language models, such as XLM-R and mT5, it has been shown that they still face difficulties when tackling typologically-distant languages, particularly in the low-resource…
Language models (LMs) are capable of acquiring elements of human-like syntactic knowledge. Targeted syntactic evaluation tests have been employed to measure how well they form generalizations about syntactic phenomena in high-resource…
Why do some languages like Czech permit free word order, while others like English do not? We address this question by pretraining transformer language models on a spectrum of synthetic word-order variants of natural languages. We observe…
The patterns in which the syntax of different languages converges and diverges are often used to inform work on cross-lingual transfer. Nevertheless, little empirical work has been done on quantifying the prevalence of different syntactic…
We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…
Mispronunciation detection (MD) models are the cornerstones of many language learning applications. Unfortunately, most systems are built for English and other major languages, while low-resourced language varieties, such as Finland Swedish…
Current accent conversion (AC) systems do not disentangle the two main sources of non-native accent: segmental and prosodic characteristics. Being able to manipulate a non-native speaker's segmental and/or prosodic channels independently is…
One of the basic tasks of computational language documentation (CLD) is to identify word boundaries in an unsegmented phonemic stream. While several unsupervised monolingual word segmentation algorithms exist in the literature, they are…