Related papers: Improving pronunciation assessment via ordinal reg…
As a subjective metric to evaluate the quality of synthesized speech, Mean opinion score~(MOS) usually requires multiple annotators to score the same speech. Such an annotation approach requires a lot of manpower and is also time-consuming.…
Conventional automatic word-naming recognition systems struggle to recognize words from post-stroke patients with aphasia because of disfluencies and mispronunciations, limiting reliable automated assessment in this population. In this…
Continual Learning (CL) involves fine-tuning pre-trained models with new data while maintaining the performance on the pre-trained data. This is particularly relevant for expanding multilingual ASR (MASR) capabilities. However, existing CL…
Natural language is characterized by compositionality: the meaning of a complex expression is constructed from the meanings of its constituent parts. To facilitate the evaluation of the compositional abilities of language processing…
Regression is a fundamental tool in scientific research. Ordinary least squares (OLS), one of the most widely used regression methods, enjoys several desirable properties, including the best linear unbiased estimator (BLUE) property. It is…
The state of the art in human computer conversation leaves something to be desired and, indeed, talking to a computer can be down-right annoying. This paper describes an approach to identifying ``opportunities for improvement'' in these…
Attention-based sequence-to-sequence models for speech recognition jointly train an acoustic model, language model (LM), and alignment mechanism using a single neural network and require only parallel audio-text pairs. Thus, the language…
Automatic Speech Recognition (ASR) systems have been examined and shown to exhibit biases toward particular groups of individuals, influenced by factors such as demographic traits, accents, and speech styles. Noise can disproportionately…
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…
Nowadays, speech is becoming a more common, if not standard, interface to technology. This can be seen in the trend of technology changes over the years. Increasingly, voice is used to control programs, appliances and personal devices…
Continuously learning new classes without catastrophic forgetting is a challenging problem for on-device acoustic event classification given the restrictions on computation resources (e.g., model size, running memory). To alleviate such an…
Evaluating ASR systems for Indian languages is challenging due to spelling variations, suffix splitting flexibility, and non-standard spellings in code-mixed words. Traditional Word Error Rate (WER) often presents a bleaker picture of…
A large number of works view the automatic assessment of speech from an utterance- or system-level perspective. While such approaches are good in judging overall quality, they cannot adequately explain why a certain score was assigned to an…
In this paper, we propose the coarse-to-fine optimization for the task of speech enhancement. Cosine similarity loss [1] has proven to be an effective metric to measure similarity of speech signals. However, due to the large variance of the…
Acoustic emotion recognition aims to categorize the affective state of the speaker and is still a difficult task for machine learning models. The difficulties come from the scarcity of training data, general subjectivity in emotion…
Training convolutional recurrent neural networks on first-order Ambisonics signals is a well-known approach when estimating the direction of arrival for speech/sound signals. In this work, we investigate whether increasing the order of…
Ordinal Regression (OR) aims to model the ordering information between different data categories, which is a crucial topic in multi-label learning. An important class of approaches to OR models the problem as a linear combination of basis…
Large Language Models utilizing reasoning techniques improve task performance but incur significant latency and token costs due to verbose generation. Existing automatic prompt optimization(APO) frameworks target task accuracy exclusively…
We consider models for which it is important, early in processing, to estimate some variables with high precision, but perhaps at relatively low rates of recall. If some variables can be identified with near certainty, then they can be…
Automatic Speech Assessment (ASA) has seen notable advancements with the utilization of self-supervised features (SSL) in recent research. However, a key challenge in ASA lies in the imbalanced distribution of data, particularly evident in…