Zobrazeno 1 - 10
of 158
pro vyhledávání: '"Hain, Thomas"'
Machine learning techniques are an active area of research for speech enhancement for hearing aids, with one particular focus on improving the intelligibility of a noisy speech signal. Recent work has shown that feature encodings from self-supervised
Externí odkaz:
http://arxiv.org/abs/2407.13333
This paper investigates the use of unsupervised text-to-speech synthesis (TTS) as a data augmentation method to improve accented speech recognition. TTS systems are trained with a small amount of accented speech training data and their pseudo-labels
Externí odkaz:
http://arxiv.org/abs/2407.04047
Autor:
Meghanani, Amit, Hain, Thomas
Self-supervised learning (SSL)-based speech models are extensively used for full-stack speech processing. However, it has been observed that improving SSL-based speech representations using unlabeled speech for content-related tasks is challenging an
Externí odkaz:
http://arxiv.org/abs/2406.09153
Autor:
Ravenscroft, William, Close, George, Goetze, Stefan, Hain, Thomas, Soleymanpour, Mohammad, Chowdhury, Anurag, Fuhs, Mark C.
One solution to automatic speech recognition (ASR) of overlapping speakers is to separate speech and then perform ASR on the separated signals. Commonly, the separator produces artefacts which often degrade ASR performance. Addressing this issue typi
Externí odkaz:
http://arxiv.org/abs/2406.08914
Autor:
Ma, Ziyang, Chen, Mingjie, Zhang, Hezhao, Zheng, Zhisheng, Chen, Wenxi, Li, Xiquan, Ye, Jiaxin, Chen, Xie, Hain, Thomas
Speech emotion recognition (SER) is an important part of human-computer interaction, receiving extensive attention from both industry and academia. However, the current research field of SER has long suffered from the following problems: 1) There are
Externí odkaz:
http://arxiv.org/abs/2406.07162
Autor:
Chen, Mingjie, Zhang, Hezhao, Li, Yuanchao, Luo, Jiachen, Wu, Wen, Ma, Ziyang, Bell, Peter, Lai, Catherine, Reiss, Joshua, Wang, Lin, Woodland, Philip C., Chen, Xie, Phan, Huy, Hain, Thomas
Speech emotion recognition is a challenging classification task with natural emotional speech, especially when the distribution of emotion types is imbalanced in the training and test data. In this case, it is more difficult for a model to learn to s
Externí odkaz:
http://arxiv.org/abs/2405.20064
Word error rate (WER) is a metric used to evaluate the quality of transcriptions produced by Automatic Speech Recognition (ASR) systems. In many applications, it is of interest to estimate WER given a pair of a speech utterance and a transcript. Prev
Externí odkaz:
http://arxiv.org/abs/2404.16743
Within the area of speech enhancement, there is an ongoing interest in the creation of neural systems which explicitly aim to improve the perceptual quality of the processed audio. In concert with this is the topic of non-intrusive (i.e. without clea
Externí odkaz:
http://arxiv.org/abs/2403.11732
Autor:
Meghanani, Amit, Hain, Thomas
Acoustic word embeddings (AWEs) are vector representations of spoken words. An effective method for obtaining AWEs is the Correspondence Auto-Encoder (CAE). In the past, the CAE method has been associated with traditional MFCC features. Representatio
Externí odkaz:
http://arxiv.org/abs/2403.08738
Autor:
Meghanani, Amit, Hain, Thomas
There is a growing interest in cost-effective self-supervised fine-tuning (SSFT) of self-supervised learning (SSL)-based speech models to obtain task-specific representations. These task-specific representations are used for robust performance on var
Externí odkaz:
http://arxiv.org/abs/2403.06260