相关论文: Data mining Mandarin tone contour shapes

The success of speech assistants requires precise recognition of a number of entities on particular contexts. A common solution is to train a class-based n-gram language model and then expand the classes into specific words or phrases.…

The use of Large Language Models (LLMs) is proliferating, yet their performance is observed to vary based on prompting styles and tones. In this study, we investigate both whether and how tonal variations in prompts lead to disparate LLM…

This study asks how self-supervised speech models represent suprasegmental categories like Mandarin lexical tone, English lexical stress, and English phrasal accents. Through a series of probing tasks, we make layer-wise comparisons of…

We use tensor analysis techniques for high-dimensional data to gain insight into pitch curves, which play an important role in linguistics research. In particular, we propose that demeaned phonetics pitch curve data can be modeled as having…

Data-driven subword segmentation has become the default strategy for open-vocabulary machine translation and other NLP tasks, but may not be sufficiently generic for optimal learning of non-concatenative morphology. We design a test suite…

With a growing focus on morphological inflection systems for languages where high-quality data is scarce, training data noise is a serious but so far largely ignored concern. We aim at closing this gap by investigating the types of noise…

This study probes the phonetic and phonological knowledge of lexical tones in TTS models through two experiments. Controlled stimuli for testing tonal coarticulation and tone sandhi in Mandarin were fed into Tacotron 2 and WaveGlow to…

In human conversational interactions, turn-taking exchanges can be coordinated using cues from multiple modalities. To design spoken dialog systems that can conduct fluid interactions it is desirable to incorporate cues from separate…

Experimental methods for estimating the impacts of text on human evaluation have been widely used in the social sciences. However, researchers in experimental settings are usually limited to testing a small number of pre-specified text…

Music Genres serve as an important meta-data in the field of music information retrieval and have been widely used for music classification and analysis tasks. Visualizing these music genres can thus be helpful for music exploration,…

This technical report presents our initial attempt to build a spoken large language model (LLM) for Taiwanese Mandarin, specifically tailored to enable real-time, speech-to-speech interaction in multi-turn conversations. Our end-to-end…

Meaning can be generated when information is related at a systemic level. Such a system can be an observer, but also a discourse, for example, operationalized as a set of documents. The measurement of semantics as similarity in patterns…

Models of bags of words typically assume topic mixing so that the words in a single bag come from a limited number of topics. We show here that many sets of bag of words exhibit a very different pattern of variation than the patterns that…

Clustering a lexicon of words is a well-studied problem in natural language processing (NLP). Word clusters are used to deal with sparse data in statistical language processing, as well as features for solving various NLP tasks (text…

We propose an alternate approach to quantifying how well language models learn natural language: we ask how well they match the statistical tendencies of natural language. To answer this question, we analyze whether text generated from…

Visual speech recognition (VSR) aims to transcribe spoken content from silent lip-motion videos and is particularly challenging in Mandarin due to severe viseme ambiguity and pervasive homophones. We propose VALLR-Pin, a two-stage Mandarin…

Increasing amount of research has shed light on machine perception of audio events, most of which concerns detection and classification tasks. However, human-like perception of audio scenes involves not only detecting and classifying audio…

Contextualizing language technologies beyond a single language kindled embracing multiple modalities and languages. Individually, each of these directions undoubtedly proliferated into several NLP tasks. Despite this momentum, most of the…

We present a multilinear statistical model of the human tongue that captures anatomical and tongue pose related shape variations separately. The model is derived from 3D magnetic resonance imaging data of 11 speakers sustaining speech…

This paper aims to use term clustering to build a modular ontology according to core ontology from domain-specific text. The acquisition of semantic knowledge focuses on noun phrase appearing with the same syntactic roles in relation to a…