相关论文: Transformer-Based Multi-Aspect Multi-Granularity N…

Grapheme-to-phoneme (G2P) models are a key component in Automatic Speech Recognition (ASR) systems, such as the ASR system in Alexa, as they are used to generate pronunciations for out-of-vocabulary words that do not exist in the…

Voice assistants increasingly use on-device Automatic Speech Recognition (ASR) to ensure speed and privacy. However, due to resource constraints on the device, queries pertaining to complex information domains often require further…

Transformer based models are the modern work horses for neural machine translation (NMT), reaching state of the art across several benchmarks. Despite their impressive accuracy, we observe a systemic and rudimentary class of errors made by…

Sentiment analysis is an important task in natural language processing. In recent works, pre-trained language models are often used to achieve state-of-the-art results, especially when training data is scarce. It is common to fine-tune on…

The acquisition of grammar has been a central question to adjudicate between theories of language acquisition. In order to conduct faster, more reproducible, and larger-scale corpus studies on grammaticality in child-caregiver…

With the development of teleconferencing and in-vehicle voice assistants, far-field multi-speaker speech recognition has become a hot research topic. Recently, a multi-channel transformer (MCT) has been proposed, which demonstrates the…

Automated explanatory feedback systems play a crucial role in facilitating learning for a large cohort of learners by offering feedback that incorporates explanations, significantly enhancing the learning process. However, delivering such…

Automatic Pronunciation Assessment (APA) is vital for computer-assisted language learning. Prior methods rely on annotated speech-text data to train Automatic Speech Recognition (ASR) models or speech-score data to train regression models.…

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…

In this work, we introduce a multi-task transformer for speech deepfake detection, capable of predicting formant trajectories and voicing patterns over time, ultimately classifying speech as real or fake, and highlighting whether its…

Methods for modeling and controlling prosody with acoustic features have been proposed for neural text-to-speech (TTS) models. Prosodic speech can be generated by conditioning acoustic features. However, synthesized speech with a large…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

Self-supervised learning models have revolutionized the field of speech processing. However, the process of fine-tuning these models on downstream tasks requires substantial computational resources, particularly when dealing with multiple…

Allophony refers to the variation in the phonetic realization of a phoneme based on its phonetic environment. Modeling allophones is crucial for atypical pronunciation assessment, which involves distinguishing atypical from typical…

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Sentence level pronunciation assessment is important for Computer Assisted Language Learning (CALL). Traditional speech pronunciation assessment, based on the Goodness of Pronunciation (GOP) algorithm, has some weakness in assessing a…

Speech recognition systems for irregularly-spelled languages like English normally require hand-written pronunciations. In this paper, we describe a system for automatically obtaining pronunciations of words for which pronunciations are not…

Recent automatic lyrics transcription (ALT) approaches focus on building stronger acoustic models or in-domain language models, while the pronunciation aspect is seldom touched upon. This paper applies a novel computational analysis on the…

Any-to-any voice conversion technologies convert the vocal timbre of an utterance to any speaker even unseen during training. Although there have been several state-of-the-art any-to-any voice conversion models, they were all based on clean…

Mispronunciation detection is an essential component of the Computer-Assisted Pronunciation Training (CAPT) systems. State-of-the-art mispronunciation detection models use Deep Neural Networks (DNN) for acoustic modeling, and a Goodness of…