no code implementations • EACL (HCINLP) 2021 • Nina Markl, Catherine Lai
Commercial Automatic Speech Recognition (ASR) systems tend to show systemic predictive bias for marginalised speaker/user groups.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 4 Feb 2024 • Alexandra Saliba, Yuanchao Li, Ramon Sanabria, Catherine Lai
Through a comparative experiment and a layer-wise accuracy analysis on two distinct corpora, IEMOCAP and ESD, we explore differences between AWEs and raw self-supervised representations, as well as the proper utilization of AWEs alone and in combination with word embeddings.
no code implementations • 7 Jul 2023 • Sarenne Wallbridge, Peter Bell, Catherine Lai
Speech is a fundamental means of communication that can be seen to provide two channels for transmitting information: the lexical channel of which words are said, and the non-lexical channel of how they are spoken.
no code implementations • 25 May 2023 • Yuanchao Li, Zeyu Zhao, Ondrej Klejch, Peter Bell, Catherine Lai
To overcome this challenge, we investigate how Automatic Speech Recognition (ASR) performs on emotional speech by analyzing the ASR performance on emotion corpora and examining the distribution of word errors and confidence scores in ASR transcripts to gain insight into how emotion affects ASR.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 25 May 2023 • Yuanchao Li, Peter Bell, Catherine Lai
In this work, we investigate the relationship between two affective attributes: personality and emotion, from a transfer learning perspective.
no code implementations • 23 May 2023 • Yaoting Wang, Yuanchao Li, Paul Pu Liang, Louis-Philippe Morency, Peter Bell, Catherine Lai
Fusing multiple modalities has proven effective for multimodal information processing.
no code implementations • 5 Oct 2022 • Yuanchao Li, Yumnah Mohamied, Peter Bell, Catherine Lai
Self-supervised speech models have grown fast during the past few years and have proven feasible for use in various downstream tasks.
no code implementations • 28 Mar 2022 • Shuvayanti Das, Jennifer Williams, Catherine Lai
We found that speech synthesis quality degrades after increasing the number of language switches within an utterance and decreasing the number of words.
no code implementations • 25 Mar 2022 • Yuanchao Li, Catherine Lai
In this paper, we perform impression recognition using a proposed cross-domain architecture on the dyadic IMPRESSION dataset.
no code implementations • 17 Mar 2022 • Yuanchao Li, Catherine Lai
In recent years, many works have investigated the feasibility of conversational robots for performing specific tasks, such as healthcare and interview.
no code implementations • 29 Oct 2021 • Yuanchao Li, Peter Bell, Catherine Lai
However, due to the scarcity of emotion labelled data and the difficulty of recognizing emotional speech, it is hard to obtain reliable linguistic features and models in this research area.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 6 Jul 2021 • Elijah Gutierrez, Pilar Oplustil-Gallegos, Catherine Lai
Text-to-Speech synthesis systems are generally evaluated using Mean Opinion Score (MOS) tests, where listeners score samples of synthetic speech on a Likert scale.
no code implementations • 1 May 2021 • Sarenne Wallbridge, Peter Bell, Catherine Lai
People convey information extremely effectively through spoken interaction using multiple channels of information transmission: the lexical channel of what is said, and the non-lexical channel of how it is said.
1 code implementation • 14 Mar 2020 • Zack Hodari, Catherine Lai, Simon King
In English, prosody adds a broad range of information to segment sequences, from information structure (e. g. contrast) to stylistic variation (e. g. expression of emotion).
no code implementations • WS 2018 • Leimin Tian, Catherine Lai, Johanna D. Moore
In particular, we build unimodal and multimodal multi-task learning models with sentiment score prediction as the main task and polarity and/or intensity classification as the auxiliary tasks.