相关论文: Discovering Lexical Similarity Through Articulator…

The effects of speaking-style variability on automatic speaker verification were investigated using the UCLA Speaker Variability database which comprises multiple speaking styles per speaker. An x-vector/PLDA (probabilistic linear…

General accent recognition (AR) models tend to directly extract low-level information from spectrums, which always significantly overfit on speakers or channels. Considering accent can be regarded as a series of shifts relative to native…

We propose the Fr\'echet Audio Distance (FAD), a novel, reference-free evaluation metric for music enhancement algorithms. We demonstrate how typical evaluation metrics for speech enhancement and blind source separation can fail to…

This paper presents a novel Dialectal Sound and Vowelization Recovery framework, designed to recognize borrowed and dialectal sounds within phonologically diverse and dialect-rich languages, that extends beyond its standard orthographic…

Artificial Neural networks are mathematical models at their core. This truismpresents some fundamental difficulty when networks are tasked with Natural Language Processing. A key problem lies in measuring the similarity or distance among…

Spoken language identification (LID) technologies have improved in recent years from discriminating largely distinct languages to discriminating highly similar languages or even dialects of the same language. One aspect that has been mostly…

The interest in text to speech synthesis increased in the world .text to speech have been developed formany popular languages such as English, Spanish and French and many researches and developmentshave been applied to those languages.…

Speaker Diarization (SD) systems are typically audio-based and operate independently of the ASR system in traditional speech transcription pipelines and can have speaker errors due to SD and/or ASR reconciliation, especially around speaker…

Graph Edit Distance (GED) is a widely used metric for measuring similarity between two graphs. Computing the optimal GED is NP-hard, leading to the development of various neural and non-neural heuristics. While neural methods have achieved…

Automatic Speech Recognition (ASR) is traditionally evaluated using Word Error Rate (WER), a metric that is insensitive to meaning. Embedding-based semantic metrics are better correlated with human perception, but decoder-based Large…

Multilingual training is effective in improving low-resource ASR, which may partially be explained by phonetic representation sharing between languages. In end-to-end (E2E) ASR systems, graphemes are often used as basic modeling units,…

Automatic Speech Recognition (ASR) systems are commonly evaluated using aggregate metrics such as Word Error Rate (WER), which do not capture the linguistic structure of errors. Fine-grained analysis, such as Part-of-Speech (PoS)-wise error…

Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…

Of all components of Prosody, Rhythm has been regarded as the hardest to address, as it is utterly linked to Pitch and Intensity. Nevertheless, Rhythm is a very good indicator of a speaker's fluency in a foreign language or even of some…

Phylogenetic trees can be reconstructed from the matrix which contains the distances between all pairs of languages in a family. Recently, we proposed a new method which uses normalized Levenshtein distances among words with same meaning…

Communication plays a vital role in human interaction. Studying language is a worthwhile task and more recently has become quantitative in nature with developments of fields like quantitative comparative linguistics and lexicostatistics.…

The category of figurative language contains many varieties, some of which are non-compositional in nature. This type of phrase or multi-word expression (MWE) includes idioms, which represent a single meaning that does not consist of the…

The ability to edit 3D assets from natural language presents a compelling paradigm to aid in the democratization of 3D content creation. However, while natural language is often effective at communicating general intent, it is poorly suited…

We propose three regularization-based speaker adaptation approaches to adapt the attention-based encoder-decoder (AED) model with very limited adaptation data from target speakers for end-to-end automatic speech recognition. The first…

Sound Event Detection (SED) is challenging in noisy environments where overlapping sounds obscure target events. Language-queried audio source separation (LASS) aims to isolate the target sound events from a noisy clip. However, this…